Hyperspectral image classification method based on local cooperative expression and neighbourhood information constraint
A technology of hyperspectral image and collaborative representation, applied in the field of hyperspectral image classification, it can solve the problems of reducing dictionary atoms, difficulty in solving, and long training time, so as to reduce the number, maintain the structure, and overcome the problem of solving the l0 norm or l1 Norm Difficulty Effects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0017] Reference figure 1 The specific implementation steps of the present invention are as follows:
[0018] Step 1. Select the test sample y from the reference image of the hyperspectral image test ∈R d , Construct the test sample neighborhood matrix T. In test sample y test In the neighborhood of, select and test sample y test M samples with smaller Euclidean distance form the neighborhood sample set matrix Ny = [ y test 1 , y test 2 , · · · y test M ] A R d X M , The neighborhood sample set matrix Ny and the test sample y test The neighborhood matrix T=[y test ,Ny]∈R d×(M+1) ,among them, Is the test sample y test The j-th sample selected in the neighborhood, j=1,2,...,M.
[0019] Step 2. Pass the dictionary D∈R d×r ,Calculate the coefficient matrix β∈R represented by the neighborhood matrix T of the test sample r×(M+1) .
[0020] 2a) Select training samples from the reference image of the hyperspectral image to ...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap