A Polarization SAR Image Classification Method Based on Multi-Feature Fusion
A technology of multi-feature fusion and classification method, which is applied in the field of polarimetric SAR image classification based on multi-feature fusion, and can solve the problems of different space, increased computing capacity, and inability to optimally separate feature vectors.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0052]The PolSAR (high-resolution polarimetric synthetic aperture radar image) data used in this embodiment is the C-band full-polarization SAR image of the Dutch Flevoland area acquired by the RadarSat-2 system in the four-polarization fine mode (resolution 5.2×7.6m) , in order to verify the implementation performance of the present invention, a region is selected from the fully polarized SAR image as the region to be classified, wherein the size of the region to be classified is 700×780, image 3 is a pseudo-color image obtained by Pauli decomposition (polarization target decomposition) of the area to be classified, Figure 4 is the corresponding ground truth reference map. The selected area to be classified includes four main features, which are: buildings, forests, farmland and water bodies. Figure 4 different grayscale regions in . At the same time, the pixels accounting for 1% of the full PolSAR image (known object types) are selected as the training sample set, and t...
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