Non-local adaptive multi-view method and system for small data set
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
An adaptive, non-local technology, applied in image data processing, computer parts, instruments, etc., can solve the problem of low reliability of SHP selection
Pending Publication Date: 2021-07-30
HANGZHOU DIANZI UNIV
View PDF0 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0005] In order to obtain high-resolution deformation information, on the basis of the deformation inversion framework of the existing SBAS technology, the present invention fully considers the time dimension and space dimension information of pixels, and aims at the problem of low reliability of SHP selection for small data, and provides effective solution strategy
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 more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0141] In this embodiment, the adaptive multi-view method for small data sets includes the following steps:
[0142] S1. For the time-series SAR images preprocessed by registration and non-coherent averaging, based on the amplitude average image, an unsupervised gray-scale method is used for image segmentation; the present invention first performs registration and amplitude correction between multiple SAR images , and then perform preprocessing such as time-dimensional incoherent intensity averaging. The specific implementation of step S1 is as follows: 1.1. Preprocessing such as multi-image SAR registration, time dimension non-coherent amplitude averaging, etc.
[0143] Due to the position deviation when the SAR system acquires data, registration processing is required before InSAR processing. In order to obtain better elevation or deformation inversion results, the registration accuracy between SAR images needs to be guaranteed within 1 / 10-1 / 8 pixel, and the current InSAR p...
Embodiment 2
[0203] Such as Figure 5 As shown, the present embodiment is a non-local adaptive multi-view system for small data sets, which includes the following modules:
[0204] Preprocessing and image segmentation module: The preprocessed time series SAR image is based on the amplitude average image, and the unsupervised gray level method is used for image segmentation; the details of the preprocessing and image segmentation module are as follows:
[0205] 1.1. The preprocessing includes multiple SAR registration and time-dimensional non-coherent amplitude averaging;
[0206] The magnitude set of N registered SAR images is expressed as
[0207] Amp=Amp 1≤i≤N (1)
[0208] In the formula, Amp i Indicates the magnitude map of the SAR image received for the ith time; in order to obtain a better image segmentation result, the discussion is based on the following mean image:
[0209]
[0210] 1.2. Unsupervised image segmentation
[0211] (1) Perform logarithmic operation on the amp...
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 invention discloses a non-local adaptive multi-view method and system for a small data set. The adaptive multi-view method for a small data set comprises the following steps of: S1, carrying out image segmentation on a time sequence SAR image which is preprocessed by registration, incoherent averaging and the like by adopting an unsupervised gray scale method based on an amplitude mean value image; S2, adaptively constructing a joint data vector based on an image segmentation result and an L1 norm between time dimension amplitude vectors; s3, for the constructed joint data vector, firstly removing abnormal values in the joint data vector, and then selecting an SHP set by adopting an AD test method; and S4, based on the selected SHP set, adaptively estimating a coherence coefficient and carrying out noise reduction processing. According to the method, information of a space dimension and information of a time dimension are considered at the same time, a reliable SHP set can be selected under the condition that the influence number is small, and therefore the coherence coefficient can be estimated in a self-adaptive mode, and interference phase diagram noise reduction can be achieved.
Description
technical field [0001] The invention belongs to the technical field of signal and information processing, and relates to a time-series interferometric synthetic aperture radar surface deformation inversion method. Specifically, on the small baseline set (Small Baseline, SBAS) technical framework, firstly, based on the image segmentation results and the L1 norm automatic Adapt to constructing a joint data vector, and remove outliers from the constructed joint data vector, then use AD detection to select the homogeneous point (Statistically Homogeneous Pixel, SHP) of the small data set, and finally perform adaptive multi-view processing based on the selected SHP set . Background technique [0002] Interferometric Synthetic Aperture Radar (InSAR) technology is a microwave remote sensing technology with great potential. It has broad application prospects. Compared with traditional InSAR technology, time-series InSAR technology uses multi-view SAR images to generate multiple in...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more