Hyperspectral remote sensing image classification method based on self-attention context network
US11783579B2 · kind B2 · utility
0Cited by
0References
5Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Mar 30, 2023 |
| Grant date | Oct 10, 2023 |
| Priority date | — |
| Expiry date | Mar 30, 2043 |
Classification
- Technology area (CPC Y)Emerging Cross-Sectional Technologies
- CPC primaryY02A40/10
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A hyperspectral remote sensing image classification method based on a self-attention context network is provided. The method constructs a spatial dependency between pixels in a hyperspectral remote sensing image by self-attention learning and context encoding, and learns global context features. For adversarial attacks in the hyperspectral remote sensing data, the proposed method has higher security and reliability to better meet the requirements of safe, reliable, and high-precision object recognition in Earth observation.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.