CN103544707A - Method for detecting change of optical remote sensing images based on contourlet transformation - Google Patents
Method for detecting change of optical remote sensing images based on contourlet transformation Download PDFInfo
- Publication number
- CN103544707A CN103544707A CN201310529322.0A CN201310529322A CN103544707A CN 103544707 A CN103544707 A CN 103544707A CN 201310529322 A CN201310529322 A CN 201310529322A CN 103544707 A CN103544707 A CN 103544707A
- Authority
- CN
- China
- Prior art keywords
- band
- image
- sub
- profile wave
- low frequency
- 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.)
- Pending
Links
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a method for detecting the change of optical remote sensing images based on contourlet information, and mainly aims to solve the problem that an existing change detection technology is not high in detection result accuracy. The method includes the steps that the two optical remote sensing images acquired at the same region and different time are preprocessed, and then a mean value ratio method difference chart and a ratio method difference chart are established respectively; N-layer contourlet transformation is conducted on the two difference charts to obtain contourlet coefficients of high frequency bands and low frequency bands of decomposition layers; different fusion operators are utilized to conduct fusion processing on the contourlet coefficients of the high frequency bands and low frequency bands respectively to obtain the fusion contourlet coefficients of the high frequency bands and the low frequency bands; inverse transformation is conducted on the fusion contourlet coefficients of the high frequency bands and the low frequency bands to obtain a fused difference chart; a fuzzy local C mean value clustering method is utilized to divide the fused difference chart to obtain the change detection result. By the adoption of the method for detecting the change of the optical remote sensing images, accuracy of the detection result is improved by improving the performance of the difference charts of the optical remote sensing images, and the method can be used for evaluating natural disasters and detecting the environment.
Description
Technical field
The invention belongs to Remote Sensing Imagery Change Detection technical field, relate in particular to a kind of remote sensing image change detecting method based on profile ripple (Contourlet) conversion.
Background technology
The change detection techniques of remote sensing images is important component parts of remote sensing images research, it is the multi-temporal remote sensing image not obtaining in the same time by the same region of comparative analysis, according to the difference between image, obtains the change information that the needed atural object of people or target occur in time.Change detection techniques can detect the variation between different times gradation of image value or local grain, obtains on this basis interesting target in the situation of change of shape, position, quantity and other attribute.These variations may be that the real change by image scene causes, also may be caused by variations such as incident angle, atmospheric conditions, sensor accuracy, surface humidities.The variation detection of remote sensing image is to detect the change information that between two width of Same Scene or several remote sensing images, temporal evolution occurs.Change testing process and mainly comprise three parts: (1) image pre-service (2) structural differences figure (3) analyzes disparity map.Wherein the pre-service of image mainly comprises geometrical registration and radiant correction, and the geometric error of removal of images reaches the coupling of the geographic coordinate of the same area different images with this, and elimination sensor self causes, the radiated noise that atmosphere radiation causes.
In existing change detecting method, when structural differences figure, the method based on arithmetical operation is the most conventional, comprises differential technique, ratioing technigue and derivative logarithm ratioing technigue thereof, and average ratioing technigue etc., wherein, average ratioing technigue is the improvement to former ratioing technigue.Yet the method for average ratio is the fuzzy edge of image when utilizing average to suppress noise, has reduced image detail information, easily will not become region and is attributed to region of variation, false drop rate is higher, has reduced to change and has detected accuracy; Ratioing technigue has also reduced the pixel value of region of variation in Background suppression region, and insensitive to region of variation, loss is higher, has reduced and has changed the precision detecting.
Generally speaking, need at present the urgent technical matters solving of those skilled in the art to be: how to construct and not only comprise the detail information that great amount of images changes but also the disparity map that can at utmost suppress noise changes detection.
Summary of the invention
Object of the present invention is exactly in order to address the above problem, a kind of remote sensing image change detecting method based on profile ripple (Contourlet) conversion is provided, so that image effective information is maximized, reduce " pseudo-variation " information, strengthen change information, Background suppression information, improve and detect accuracy and accuracy of detection.
The technical thought that realizes the object of the invention is: adopt the image interfusion method based on profile wave convert, the disparity map with ratioing technigue structure and average are merged than the disparity map of method structure, realize the variation of remote sensing image is detected.Concrete steps comprise as follows:
Step 1, the two width remote sensing images that same region different time is obtained carry out filtering and noise reduction, and the pre-service of radiant correction and geometrical registration obtains pretreated two width image X
a, X
b.
Step 2, utilizes pretreated two width image configuration ratioing technigue disparity map X
l.
Step 3, utilizes pretreated two width image configuration averages than method disparity map X
m.
Step 4, respectively correlative value method disparity map X
l, average is than method disparity map X
mcarry out N layer profile Wave Decomposition, obtain the profile wave system number of every width disparity map multi-direction multiple dimensioned decomposition in high frequency band and low-frequency band on N decomposition layer, N=5.
Step 5, profile wave system number to high frequency band and low-frequency band carries out fusion treatment with different fusion operators, the method of low-frequency band profile ripple coefficients by using being averaged merges, obtain low-frequency band and merge profile wave system number, to high frequency band profile ripple coefficients by using, select the method for neighboring region energy minimum to carry out fusion treatment, obtain high frequency band and merge profile wave system number;
Step 6, the profile wave system that is generated fused image by profile ripple is counted Y<sub TranNum="65">f</sub>, Y<sub TranNum="66">f</sub>by low frequency coefficient Y<sub TranNum="67">f</sub>?<1} and high frequency coefficient<img TranNum="68" file="BDA0000405586010000021.GIF" he="85" img-content="drawing" img-format="GIF" inline="yes" orientation="portrait" wi="262"/>form, k=2 wherein, 3,4,5,6, N=1,2,3,4,5, t=1,2 ..., 2<sup TranNum="69">n</sup>, allow k, N, t travel through these values, can obtain overall profile wave system and count Y<sub TranNum="70">f</sub>.
Step 7, counts Y by the profile wave system obtaining after merging
fcarry out contrary profile wave convert, also referred to as Image Reconstruction, obtain merging rear disparity map X
f.
Step 8, uses fuzzy Local C means clustering method to merging rear disparity map X
fcarry out image and cut apart, generate and change testing result figure, complete the final detection to two width remote sensing image change informations.
The present invention compared with prior art tool has the following advantages:
1, the present invention is owing to having adopted the image fusion technology of decomposing based on profile wave convert, on time and space, decompose frequency, can easier extraction detailed information, can well preserve the detailed information of image, thereby obtain the variation testing result that accuracy is higher.
2, the present invention, owing to utilizing the directivity of profile Wave Decomposition, has this visual characteristic of different resolution for human eye to the high fdrequency component of different directions, can obtain the better fused images of visual effect.
3, the present invention is owing to selecting different suitable fusion rule fused images, the background information of inhibition region of variation that can be to a greater extent, strengthen the change information of region of variation, make the loss of ratioing technigue and average more complementary than the false drop rate of method, obtained higher accuracy of detection.
Accompanying drawing explanation
Fig. 1 is the general flow chart of realizing of the present invention.
Embodiment
Below in conjunction with accompanying drawing and embodiment, the invention will be further described.
Referring to accompanying drawing, implementation of the present invention and advantage are described in detail.
With reference to Fig. 1, performing step of the present invention is as follows:
Step 1, the two width remote sensing images that same region different time is obtained carry out filtering and noise reduction, and the pre-service of radiant correction and geometrical registration obtains pretreated two width image X
a, X
b.
Geometric error that can removal of images by pre-service, to reach the coupling to the geographic coordinate of the same area different images, eliminates the radiated noise that noise that sensor self causes and atmosphere radiation cause.
Step 2, utilizes pretreated two width image configuration ratioing technigue disparity map X
l.Building method is:
By image X
ain be positioned at the gray-scale value X of the pixel (i, j) of the capable j of i row
a(i, j) and corresponding image X
bin be positioned at the gray-scale value X of the pixel of the capable j of i row
b(i, j), by ratio computing
obtain ratioing technigue disparity map X
lin be positioned at the gray-scale value X of the pixel (i, j) of the capable j of i row
l(i, j), if X
l(i, j) is 1, presentation video X
ain this pixel do not change over time, otherwise, think image X
ain this pixel there is variation; To image X
awith image X
bin each be positioned at the capable j of i row pixel gray-scale value from left to right, all carry out from top to bottom difference computing, obtain logarithm ratio difference figure X
l.
Step 3, utilizes pretreated two width image configuration averages than method disparity map X
m.Building method is:
By image X
ain be positioned at the gray-scale value X of the pixel (i, j) of the capable j of i row
a(i, j) and corresponding image X
bin be positioned at the gray-scale value X of the pixel of the capable j of i row
b(i, j), by the computing of average ratio
μ wherein
a(i, j), μ
b(i, j) is respectively image A, and the neighborhood territory pixel mean value of B obtains average ratioing technigue disparity map X
min be positioned at the gray-scale value X of the pixel (i, j) of the capable j of i row
m(i, j), if X
m(i, j) close to 0, presentation video X
ain be positioned at the capable j of i row pixel do not change over time, otherwise, if X
m(i, j), much larger than 0, thinks that variation has occurred this pixel; To image X
awith image X
bin each be positioned at the capable j of i row pixel gray-scale value from left to right, all carry out from top to bottom this computing, structure average is than method disparity map X
m.
Step 4, respectively correlative value method disparity map X
l, average is than method disparity map X
mcarry out N layer profile Wave Decomposition, obtain the profile wave system number of every width disparity map multi-direction multiple dimensioned decomposition in high frequency band and low-frequency band on N decomposition layer, N=5.
4.1 at ground floor, i.e. N=1, by ratioing technigue disparity map X
lresolve into a low frequency sub-band image
with a logical sub-band images of band
to be with logical sub-band images
carry out 2
nlevel Directional Decomposition, in this case 2 Directional Decompositions, obtain 2 high frequency band profile wave system numbers
t=1 wherein, 2; By average than method disparity map X
mresolve into a low frequency sub-band image
with a logical sub-band images of band
to be with logical sub-band images
carry out 2
nlevel Directional Decomposition, in this case 2 Directional Decompositions, obtain 2 high frequency band profile wave system numbers
t=1 wherein, 2.
4.2 at the second layer, i.e. N=2, by ratioing technigue disparity map X
lthe low frequency sub-band image generating through step 4.1
resolve into a low frequency sub-band image
with a logical sub-band images of band
obtain 4 high frequency band profile wave system numbers
t=1 wherein, 2,3,4; By average than method disparity map X
mthe low frequency sub-band image generating through step 4.1
resolve into a low frequency sub-band image
with a logical sub-band images of band
obtain 4 high frequency band profile wave system numbers
t=1 wherein, 2,3,4;
4.3 at the 3rd layer, i.e. N=3, by ratioing technigue disparity map X
lthe low frequency sub-band image generating through step 4.2
resolve into a low frequency sub-band image
with a logical sub-band images of band
obtain 8 high frequency band profile wave system numbers
t=1 wherein, 2 ..., 8; By average than method disparity map X
mthe low frequency sub-band image generating through step 4.2
resolve into a low frequency sub-band image
with a logical sub-band images of band
obtain 8 high frequency band profile wave system numbers
t=1 wherein, 2 ..., 8;
4.4 at the 4th layer, i.e. N=4, by ratioing technigue disparity map X
lthe low frequency sub-band image generating through step 4.3
resolve into a low frequency sub-band image
with a logical sub-band images of band
obtain 16 high frequency band profile wave system numbers
t=1 wherein, 2 ..., 16; By average than method disparity map X
mthe low frequency sub-band image generating through step 4.3
resolve into a low frequency sub-band image
with a logical sub-band images of band
obtain 16 high frequency band profile wave system numbers
t=1 wherein, 2 ..., 16;
4.5 at layer 5, i.e. N=5, by ratioing technigue disparity map X
lthe low frequency sub-band image generating through step 4.4
resolve into a low frequency sub-band image
with a logical sub-band images of band
obtain a low-frequency band profile wave system number
with 32 high frequency band profile wave system numbers
t=1 wherein, 2 ..., 32; By averaging method ratio figure X
mthe low frequency sub-band image generating through step 4.4
resolve into a low frequency sub-band image
with a logical sub-band images of band
obtain a low-frequency band profile wave system number
with 16 high frequency band profile wave system numbers
t=1 wherein, 2 ..., 32.
Step 5, profile wave system number to high frequency band and low-frequency band carries out fusion treatment with different fusion operators, the method of low-frequency band profile ripple coefficients by using being averaged merges, obtain low-frequency band and merge profile wave system number, to high frequency band profile ripple coefficients by using, select the method for neighboring region energy minimum to carry out fusion treatment, obtain high frequency band and merge profile wave system number;
5.1 for low-frequency band, obtains low frequency profile wave system number, that is: by being averaged rule fusion
Wherein
with
be respectively Y
mand Y
llow frequency part, because low frequency profile wave system is counted the profile information of representative image, the changing unit that comprises image, the present invention counts the average rule of utilization to low frequency profile wave system and is intended to strengthen fused images low frequency part, strengthens the information of changing unit;
5.2 for high frequency band, presses the fusion of neighboring region energy minimum principle rule and obtains high frequency coefficient, that is:
Wherein
represent that profile wave system that coordinate is positioned at (i, j) pixel counts the energy of M * N neighborhood,
with
be respectively Y
land Y
mhFS, represent the coefficient of t the direction that N layer in profile Wave Decomposition decomposes, k=2 wherein, 3,4,5,6, N=1,2,3,4,5, t=1,2 ..., 2
ndetailed information due to high frequency coefficient representative image, comprise edge and lines in image, the present invention chooses the information that coefficient that in source images, neighboring region energy is less can Background suppression region (not region of variation) as the coefficient of fused image, region of variation and background area just can present larger difference like this, are convenient to follow-up classification and process.
Step 6, the profile wave system that is generated fused image by profile ripple is counted Y<sub TranNum="206">f</sub>, Y<sub TranNum="207">f</sub>by low frequency coefficient Y<sub TranNum="208">f</sub>?<1} and high frequency coefficient<img TranNum="209" file="BDA0000405586010000055.GIF" he="86" img-content="drawing" img-format="GIF" inline="yes" orientation="portrait" wi="262"/>form, k=2 wherein, 3,4,5,6, N=1,2,3,4,5, t=1,2 ..., 2<sup TranNum="210">n</sup>, allow k, N, t travel through these values, can obtain overall profile wave system and count Y<sub TranNum="211">f</sub>.
Step 7, counts Y by the profile wave system obtaining after merging
fcarry out contrary profile wave convert, also referred to as Image Reconstruction, obtain merging rear disparity map X
f.
Step 8, uses fuzzy Local C means clustering method to merging rear disparity map X
fcarry out image and cut apart, generate and change testing result figure, complete the final detection to two width remote sensing image change informations.
In existing remote sensing image change detecting method, Pixel-level analysis is the most general, yet Pixel-level analysis can not fully demonstrate the relevant information of image and express details.Profile wave convert is as a kind of novel multiple dimensioned, and multiresolution analysis instrument, possesses multiresolution, locality threshold sampling characteristic, and multidirectional and anisotropy, can sparsely express two dimensional image.Remote sensing images have and contain much information, the feature that image detail is abundant, and profile wave convert has abundant coefficient and expresses image and can be by the details of less coefficient presentation video like this.In conjunction with remote sensing image, change the object detecting, expand region of variation and the difference of region of variation not, and then region of variation is never split in region of variation, the present invention introduces profile wave convert and is applied in the construction process of remote sensing image disparity map, the present invention uses the fusion based on profile wave convert can use the information of several source images, and under applicable fusion rule guides, can from source images, obtain to the full extent Significant Change information.
The present invention uses image fusion technology (employing profile wave convert) that multiple disparity map is merged, and can make full use of the advantage of each source images, and the effective information of image is maximized, and final analyzing and processing precision is made moderate progress, and improves accuracy of detection.
Although above-mentioned, by reference to the accompanying drawings the specific embodiment of the present invention is described; but be not limiting the scope of the invention; one of ordinary skill in the art should be understood that; on the basis of technical scheme of the present invention, those skilled in the art do not need to pay various modifications that creative work can make or distortion still in protection scope of the present invention.
Claims (4)
1. the remote sensing image change detecting method based on profile wave convert, is characterized in that, comprises the following steps:
(1) the two width remote sensing images that same region different time obtained carry out filtering and noise reduction, and the pre-service of radiant correction and geometrical registration obtains pretreated two width image X
a, X
b;
(2) utilize pretreated two width image configuration ratioing technigue disparity map X
l;
(3) utilize pretreated two width image configuration averages than method disparity map X
m;
(4) difference correlative value method disparity map X
l, average is than method disparity map X
mcarry out N layer profile Wave Decomposition, obtain the profile wave system number of every width disparity map multi-direction multiple dimensioned decomposition in high frequency band and low-frequency band on N decomposition layer, N=5;
(5) the profile wave system number of high frequency band and low-frequency band is carried out to fusion treatment with different fusion operators, the method of low-frequency band profile ripple coefficients by using being averaged merges, obtain low-frequency band and merge profile wave system number, to high frequency band profile ripple coefficients by using, select the method for neighboring region energy minimum to carry out fusion treatment, obtain high frequency band and merge profile wave system number;
(6) by the profile wave system of profile ripple generation fused image, count Y<sub TranNum="235">f</sub>, Y<sub TranNum="236">f</sub>by low frequency coefficient Y<sub TranNum="237">f</sub>?<1} and high frequency coefficient<img TranNum="238" file="FDA0000405586000000012.GIF" he="79" id="ifm0001" img-content="drawing" img-format="GIF" inline="yes" orientation="portrait" wi="258"/>form, k=2 wherein, 3,4,5,6, N=1,2,3,4,5, t=1,2 ..., 2<sup TranNum="239">n</sup>, allow k, N, t travel through these values, can obtain overall profile wave system and count Y<sub TranNum="240">f</sub>;
(7) the profile wave system obtaining after merging is counted to Y
fcarry out contrary profile wave convert, also referred to as Image Reconstruction, obtain merging rear disparity map X
f;
(8) use fuzzy Local C means clustering method to merging rear disparity map X
fcarry out image and cut apart, generate and change testing result figure, complete the final detection to two width remote sensing image change informations.
2. a kind of remote sensing image change detecting method based on profile wave convert as claimed in claim 1, is characterized in that, what wherein step (3) was described utilizes pretreated two width image configuration averages than method disparity map X
m, make is:
By image X
ain be positioned at the gray-scale value X of the pixel (i, j) of the capable j of i row
a(i, j) and corresponding image X
bin be positioned at the gray-scale value X of the pixel of the capable j of i row
b(i, j), by the computing of average ratio
μ wherein
a(i, j), μ
b(i, j) is respectively image A, and the neighborhood territory pixel mean value of B obtains average ratioing technigue disparity map X
min be positioned at the gray-scale value X of the pixel (i, j) of the capable j of i row
m(i, j), if X
m(i, j) close to 0, presentation video X
ain be positioned at the capable j of i row pixel do not change over time, otherwise, if X
m(i, j), much larger than 0, thinks that variation has occurred this pixel; To image X
awith image X
bin each be positioned at the capable j of i row pixel gray-scale value from left to right, all carry out from top to bottom this computing, structure average is than method disparity map X
m.
3. a kind of remote sensing image change detecting method based on profile wave convert as claimed in claim 1, is characterized in that, wherein the described difference correlative value method disparity map X of step (4)
l, average is than method disparity map X
mcarry out N layer profile Wave Decomposition, carry out as follows:
(4a) at ground floor, i.e. N=1, by ratioing technigue disparity map X
lresolve into a low frequency sub-band image
with a logical sub-band images of band
, will be with logical sub-band images
carry out 2
nlevel Directional Decomposition, in this case 2 Directional Decompositions, obtain 2 high frequency band profile wave system numbers
t=1 wherein, 2; By average than method disparity map X
mresolve into a low frequency sub-band image
with a logical sub-band images of band
to be with logical sub-band images
carry out 2
nlevel Directional Decomposition, in this case 2 Directional Decompositions, obtain 2 high frequency band profile wave system numbers
, t=1 wherein, 2.
(4b) at the second layer, i.e. N=2, by ratioing technigue disparity map X
lthe low frequency sub-band image generating through step 4.1
resolve into a low frequency sub-band image
with a logical sub-band images of band
obtain 4 high frequency band profile wave system numbers
t=1 wherein, 2,3,4; By average than method disparity map X
mthe low frequency sub-band image generating through step 4.1
resolve into a low frequency sub-band image
with a logical sub-band images of band
obtain 4 high frequency band profile wave system numbers
t=1 wherein, 2,3,4;
(4c) at the 3rd layer, i.e. N=3, by ratioing technigue disparity map X
lthe low frequency sub-band image generating through step 4.2
resolve into a low frequency sub-band image
with a logical sub-band images of band
obtain 8 high frequency band profile wave system numbers
t=1 wherein, 2 ..., 8; By average than method disparity map X
mthe low frequency sub-band image generating through step 4.2
resolve into a low frequency sub-band image
with a logical sub-band images of band
obtain 8 high frequency band profile wave system numbers
t=1 wherein, 2 ..., 8;
(4d) at the 4th layer, i.e. N=4, by ratioing technigue disparity map X
lthe low frequency sub-band image generating through step 4.3
resolve into a low frequency sub-band image
with a logical sub-band images of band
obtain 16 high frequency band profile wave system numbers
t=1 wherein, 2 ..., 16; By average than method disparity map X
mthe low frequency sub-band image generating through step 4.3
resolve into a low frequency sub-band image
with a logical sub-band images of band
obtain 16 high frequency band profile wave system numbers
t=1 wherein, 2 ..., 16;
(4e) at layer 5, i.e. N=5, by ratioing technigue disparity map X
lthe low frequency sub-band image generating through step 4.4
resolve into a low frequency sub-band image
with a logical sub-band images of band
obtain a low-frequency band profile wave system number
with 32 high frequency band profile wave system numbers
t=1 wherein, 2 ..., 32; By averaging method ratio figure X
mthe low frequency sub-band image generating through step 4.4
resolve into a low frequency sub-band image
with a logical sub-band images of band
obtain a low-frequency band profile wave system number
with 16 high frequency band profile wave system numbers
t=1 wherein, 2 ..., 32.
4. a kind of remote sensing image change detecting method based on profile wave convert as claimed in claim 1, it is characterized in that, wherein the described profile wave system number to high frequency band and low-frequency band of step (5) carries out fusion treatment with different fusion operators, carries out in the following manner:
(5a), for low-frequency band, by being averaged rule fusion, obtain low frequency profile wave system number, that is:
Wherein
with
be respectively Y
mand Y
llow frequency part, because low frequency profile wave system is counted the profile information of representative image, the changing unit that comprises image, the present invention counts the average rule of utilization to low frequency profile wave system and is intended to strengthen fused images low frequency part, strengthens the information of changing unit;
(5b), for high frequency band, press the fusion of neighboring region energy minimum principle rule and obtain high frequency coefficient, that is:
Wherein
represent that profile wave system that coordinate is positioned at (i, j) pixel counts the energy of M * N neighborhood,
with
be respectively Y
land Y
mhFS, represent the coefficient of t the direction that N layer in profile Wave Decomposition decomposes, k=2 wherein, 3,4,5,6, N=1,2,3,4,5, t=1,2 ..., 2
n.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310529322.0A CN103544707A (en) | 2013-10-31 | 2013-10-31 | Method for detecting change of optical remote sensing images based on contourlet transformation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310529322.0A CN103544707A (en) | 2013-10-31 | 2013-10-31 | Method for detecting change of optical remote sensing images based on contourlet transformation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103544707A true CN103544707A (en) | 2014-01-29 |
Family
ID=49968127
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310529322.0A Pending CN103544707A (en) | 2013-10-31 | 2013-10-31 | Method for detecting change of optical remote sensing images based on contourlet transformation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103544707A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104331864A (en) * | 2014-10-21 | 2015-02-04 | 西安电子科技大学 | Breast imaging processing based on non-subsampled contourlet and visual salient model |
| CN110599412A (en) * | 2019-08-15 | 2019-12-20 | 中国科学院遥感与数字地球研究所 | Remote sensing data processing method and system based on unmanned aerial vehicle |
| CN113538306A (en) * | 2021-06-15 | 2021-10-22 | 西安电子科技大学 | Multi-image fusion method for SAR image and low-resolution optical image |
| CN114049568A (en) * | 2021-11-29 | 2022-02-15 | 中国平安财产保险股份有限公司 | Object shape change detection method, device, equipment and medium based on image comparison |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080224923A1 (en) * | 2006-07-07 | 2008-09-18 | Aprile Angelo | Method and apparatus for detection of moving objects by sar images |
| CN102629377A (en) * | 2012-03-01 | 2012-08-08 | 西安电子科技大学 | Remote sensing image change detection method based on saliency measurement |
| CN102800074A (en) * | 2012-07-12 | 2012-11-28 | 西安电子科技大学 | Synthetic aperture radar (SAR) image change detection difference chart generation method based on contourlet transform |
-
2013
- 2013-10-31 CN CN201310529322.0A patent/CN103544707A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080224923A1 (en) * | 2006-07-07 | 2008-09-18 | Aprile Angelo | Method and apparatus for detection of moving objects by sar images |
| CN102629377A (en) * | 2012-03-01 | 2012-08-08 | 西安电子科技大学 | Remote sensing image change detection method based on saliency measurement |
| CN102800074A (en) * | 2012-07-12 | 2012-11-28 | 西安电子科技大学 | Synthetic aperture radar (SAR) image change detection difference chart generation method based on contourlet transform |
Non-Patent Citations (1)
| Title |
|---|
| 李艳灵等: ""基于轮廓波变换的模糊聚类图像分割"", 《信阳师范学院学报（自然科学版）》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104331864A (en) * | 2014-10-21 | 2015-02-04 | 西安电子科技大学 | Breast imaging processing based on non-subsampled contourlet and visual salient model |
| CN104331864B (en) * | 2014-10-21 | 2018-11-23 | 西安电子科技大学 | Based on the processing of the breast image of non-down sampling contourlet and the significant model of vision |
| CN110599412A (en) * | 2019-08-15 | 2019-12-20 | 中国科学院遥感与数字地球研究所 | Remote sensing data processing method and system based on unmanned aerial vehicle |
| CN113538306A (en) * | 2021-06-15 | 2021-10-22 | 西安电子科技大学 | Multi-image fusion method for SAR image and low-resolution optical image |
| CN113538306B (en) * | 2021-06-15 | 2024-02-13 | 西安电子科技大学 | SAR image and low-resolution optical image multi-image fusion method |
| CN114049568A (en) * | 2021-11-29 | 2022-02-15 | 中国平安财产保险股份有限公司 | Object shape change detection method, device, equipment and medium based on image comparison |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102800074B (en) | Synthetic aperture radar (SAR) image change detection difference chart generation method based on contourlet transform | |
| CN102436652B (en) | Automatic registering method of multisource remote sensing images | |
| CN103049898B (en) | Method for fusing multispectral and full-color images with light cloud | |
| CN102063715B (en) | Method for fusing typhoon cloud pictures based on NSCT (Nonsubsampled Controurlet Transformation) and particle swarm optimization algorithm | |
| JP2015513680A (en) | Foliage penetration based on 4D lidar data set | |
| CN101777181B (en) | Ridgelet bi-frame system-based SAR image airfield runway extraction method | |
| CN106296655A (en) | Based on adaptive weight and the SAR image change detection of high frequency threshold value | |
| CN103366353A (en) | Infrared image and visible-light image fusion method based on saliency region segmentation | |
| CN102750705A (en) | Optical remote sensing image change detection based on image fusion | |
| CN103544707A (en) | Method for detecting change of optical remote sensing images based on contourlet transformation | |
| CN101359399A (en) | Cloud-removing method for optical image | |
| CN102945548A (en) | Directional pyramid filtering-based image processing method and device | |
| CN103489178A (en) | Method and system for image registration | |
| CN103500440A (en) | Method for eliminating cloud and haze of atmospheric degraded image | |
| CN103400383A (en) | SAR (synthetic aperture radar) image change detection method based on NSCT (non-subsampled contourlet transform) and compressed projection | |
| CN103824302A (en) | SAR (synthetic aperture radar) image change detecting method based on direction wave domain image fusion | |
| CN103839243A (en) | Multi-channel satellite cloud picture fusion method based on Shearlet conversion | |
| CN104036461B (en) | A kind of Infrared Complex Background suppressing method based on Federated filter | |
| Maltezos et al. | Automatic detection of building points from LiDAR and dense image matching point clouds | |
| CN102663385A (en) | Detection method for spot target on satellite | |
| CN105184804A (en) | Sea surface small target detection method based on airborne infrared camera aerially-photographed image | |
| CN101739667B (en) | Non-downsampling contourlet transformation-based method for enhancing remote sensing image road | |
| Elhabiby et al. | Second generation curvelet transforms Vs Wavelet transforms and Canny edge detector for edge detection from worldview-2 data | |
| CN106156758A (en) | A kind of tidal saltmarsh method in SAR coast chart picture | |
| CN103310414A (en) | Image enhancement method based on directionlet transform and fuzzy theory |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140129 |