Change Detection Method of Polarization SAR Image Based on Depth Curvelet Difference DSN
An image change detection and depth technology, applied in the field of image processing, can solve the problems of high imaging conditions of two polarimetric synthetic aperture radar SAR images, no consideration of multi-scale features of polarimetric synthetic aperture radar, and low change detection accuracy. , to achieve the effect of strong generalization performance, reduced false detection rate, and simple calculation.
Active Publication Date: 2019-10-25
XIDIAN UNIV
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Since this method only considers the local features of the two images, although it can obtain better change detection results, the disadvantage of this method is that it does not consider the unique multi-scale features of polarimetric synthetic aperture radar SAR images. , so there is still the problem of low accuracy of change detection
Although this method extracts the unique polarization state of polarimetric SAR SAR images, it can better detect polarimetric SAR SAR images with obvious polarization state characteristics, but the method still has the disadvantages of , the calculation process is cumbersome, and the imaging conditions for two polarization SAR images are relatively high
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0039] The present invention will be further described below in conjunction with the accompanying drawings.
[0040] refer to figure 1 , the concrete steps that the present invention realizes are as follows.
[0041] Step 1, input polarimetric SAR SAR images.
[0042] Input two unprocessed polarimetric SAR images of the same area with different time phases I 1 and I 2 .
[0043] Step 2, obtain the polarized scattering matrix.
[0044] Using remote sensing image registration software, the polarimetric synthetic aperture radar SAR image I 1 and I 2 Perform the registration operation to obtain the registered polarization scattering matrix S 1 and S 2 .
[0045] Step 3, obtain the polarization covariance matrix.
[0046] Using the matrix transformation method, the polarization scattering matrix S 1 and S 2 Convert to polarization covariance matrix C 1 and C 2 .
[0047] The specific steps of the matrix transformation method are as follows, where the polarization covar...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present invention discloses a polarizing SAR image change detection method based on a deep curvelet differential DSN which mainly solves the problems that the polarizing SAR image change detectionin a conventional method does not consider the proper multi-scale characteristics of the polarizing SAR images, and the detection precision is not high. The method of the present invention concretelycomprises the steps of (1) inputting a polarizing SAR image; (2) obtaining a polarization scattering matrix; (3) calculating a polarization covariance matrix; (4) obtaining the filtered polarizationcovariance matrix; (5) calculating the polarization covariance matrix after the normalization; (6) constructing a data set; (7) constructing a multi-scale differential change detection model; (8) training the multi-scale differential change detection model; (9) obtaining a change detection result. The method of the present invention has the advantages of being good to extract the multi-scale characteristics of the polarizing SAR images, and being high in detection precision.
Description
technical field [0001] The present invention belongs to the technical field of image processing, and further relates to a polarization synthetic aperture radar SAR (Synthetic Aperture Radar) image change detection based on depth curvelet differential depth stack network DSN (Deep Stack Network) in the technical field of remote sensing image change detection method. The invention can realize the detection of different regions of two polarized synthetic aperture radar SAR images acquired in different time phases, and can be widely used in the fields of land utilization, military monitoring, urban planning, post-disaster reconstruction and the like. Background technique [0002] The change detection of polarimetric synthetic aperture radar SAR images refers to the detection and analysis of ground changes by using two polarimetric synthetic aperture radar SAR images of different phases in the same area. Compared with ordinary optical remote sensing technology, polarimetric SAR ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T7/30
CPCG06T7/0002G06T7/30G06T2207/10044G06T2207/20024G06T2207/20081
Inventor 焦李成屈嵘张佳琪唐旭杨淑媛侯彪马文萍刘芳尚荣华陈璞花张丹古晶
Owner XIDIAN UNIV