A high spatial-high spectral resolution remote sensing image eigendecomposition method and system
A high spatial resolution, hyperspectral remote sensing technology, applied in the field of eigendecomposition of high spatial-hyperspectral resolution remote sensing images, can solve problems such as inability to decompose, achieve improved spatial resolution, avoid aliasing, and maintain ground objects The effect of borders
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach 1
[0072] Embodiment 1: Combining figure 1 This embodiment will be described. A method for eigendecomposition of remote sensing images with high spatial-hyperspectral resolution described in this embodiment includes the following steps:
[0073] Step 1: Obtain panchromatic remote sensing images and hyperspectral remote sensing images, analyze the spatial information of the panchromatic remote sensing images and the spectral information of the hyperspectral remote sensing images, use the spatial information of the panchromatic remote sensing images to construct the spatial structure consistency constraint, and use the hyperspectral remote sensing images. The spectral information of the remote sensing image constructs the spectral consistency constraint, which fully considers the spectral characteristics of the hyperspectral remote sensing image and the spatial characteristics of the panchromatic remote sensing image, and goes to step 2;
[0074] Step 2: Calculate the similarity ma...
specific Embodiment approach 2
[0076] Specific implementation mode 2: Combining figure 1 This embodiment will be described. In a method for eigendecomposition of remote sensing images with high spatial-hyperspectral resolution described in this embodiment, step 1 includes:
[0077] Step 11: Obtain panchromatic remote sensing images and hyperspectral remote sensing images, and analyze the spatial information of the panchromatic remote sensing images and the spectral information of the hyperspectral remote sensing images;
[0078] Step 12: According to the spatial information of the panchromatic remote sensing image and the spectral information of the hyperspectral remote sensing image obtained in the step 11, respectively calculate the spatial information consistency constraint and the spectral information consistency constraint;
[0079] The high spatial resolution hyperspectral remote sensing image (HR-HSI) can be decomposed into two intrinsic components, namely the light and dark components and the reflec...
specific Embodiment approach 3
[0106] Specific implementation three: combination figure 1 This embodiment is described. In the method for eigendecomposition of remote sensing images with high spatial-hyperspectral resolution described in this embodiment, step 2 includes:
[0107] For the reflectance component, the same material has the same reflectance, so the reflectance component has a strong correlation in the local neighborhood, and its linear relationship is expressed as follows:
[0108]
[0109] Among them, ω i Represents a local window of size (2r+1)×(2r+1) centered on pixel i;
[0110] W(i,j) represents the similarity between pixel i and pixel j, W∈R N×N ;
[0111] represents the logarithmic domain reflectance component of the ith pixel;
[0112] represents the logarithmic domain reflectance component of the jth pixel;
[0113] Based on the optic nerve (Retinex) theory, the reflectivity of object materials generally only changes greatly at the edge, and the reflectivity can be regarded ...
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