Hyperspectral image dimension reduction method and device based on self-adaptive collaborative graph discriminant analysis
A hyperspectral image and discriminant analysis technology, applied in the field of remote sensing image processing, can solve problems affecting the classification accuracy of hyperspectral images, achieve the effect of enhancing inter-class judgment ability, enhancing discrimination ability, and reducing computational complexity
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0075] This embodiment discloses a hyperspectral image dimensionality reduction method based on adaptive synergy graph discriminant analysis. On the basis of Embodiment 1, the following technical features are also disclosed:
[0076] This embodiment adopts the internationally recognized standard public data set University of Pavia, which has nine classes (Asphalt, Meadows, Gravel, Trees, Painted Metal Sheets, Bare Soil, Bitumen, Self-Blocking Bricks, Shadows), and the sample numbers are respectively 6631, 18649, 2099, 3064, 1345, 5029, 1330, 3682 and 947.
[0077] figure 2 (b) is the result obtained from the Tikhonov regular graph weight coefficient matrix divided into categories. The data used are the first three categories (Asphalt, Meadows, and Gravel) from the public dataset University of Pavia. according to figure 2, the graph weight coefficient matrices of both CGDA and ACGDA have a block-diagonal structure (ie, three block regions in the diagonal direction correspo...
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