NSST (NonsubsampledShearlet Transform) domain MRF (Markov Random Field) and adaptive threshold fused remote sensing image change detection method
An adaptive threshold and remote sensing image technology, applied to instruments, character and pattern recognition, computer components, etc., can solve the problems of not considering the relationship between features of different scales, affecting the change detection results, and not being able to obtain the change detection results
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0063] The present invention is a remote sensing image change detection method of fusion of NSST domain MRF and adaptive threshold value, which mainly processes remote sensing images. The image processing requires a large-capacity computer as hardware support, and uses matlab and other software to realize image processing. see figure 1 , remote sensing image change detection includes the following steps:
[0064] Step 1, for the two input remote sensing images X of the same area with different phases of size I×J that have been registered 1 and x 2 ,Such as figure 2 (a) and figure 2 As shown in (b), the image X 1 and x 2 The pixel gray value X at the corresponding position (m,n) in the space 1 (m,n) and X 2 (m, n) to calculate the difference and get the difference X d (m,n)=|X 1 (m,n)-X 2 (m, n)|, where, m and n are the row and column numbers of the remote sensing image respectively, m=1, 2,..., I, n=1, 2,..., J, thus obtaining a difference image x d .
[0065] S...
Embodiment 2
[0114] The remote sensing image change detection method of NSST domain MRF and adaptive threshold fusion is the same as embodiment 1, refer to figure 1 , the implementation steps of the present invention are further described as follows:
[0115] Among them, in step 5, a high-frequency adaptive threshold classification map B of the sth layer is obtained h,s The specific operation is:
[0116] (5a) Using the high-frequency initial classification map of the s-th layer obtained in step 3, calculate the high-frequency sub-band D of this layer h,s The prior probability of the variation class in and the prior probabilities of the invariant class
[0117] p ( ω h , c s ) = N h , c s ...
Embodiment 3
[0140] The remote sensing image change detection method of NSST domain MRF and adaptive threshold value fusion is the same as embodiment 1-2, wherein the value of the final iteration number K in the step (6a) is selected as 15, and the MRF classification map of each layer that obtains like this and K= Compared with the same layer, the MRF classification diagrams of each layer obtained at 5 o'clock have fewer missed detections and increased false detections; the value of K is selected as 15, and the final MRF classification diagrams obtained by intersection and fusion of the MRF classification diagrams of all decomposed layers are the same as K= Compared with the final MRF classification map at 5 o'clock, the missed detection is reduced and the false detection is increased; the value of K selected as 15 has little effect on the final change detection result map, but its efficiency is reduced, that is to say, the selection of K Efficiency is slightly affected when the value is in...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com