Small sample hyperspectral classification method based on data enhancement
A hyperspectral classification and small-sample technology, which is applied to instruments, scene recognition, calculations, etc., can solve problems such as imperfect cognition of hyperspectral data
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment 1
[0069] Specific embodiment one: the present invention provides a small sample hyperspectral classification method based on data enhancement, such as figure 1 and figure 2 shown.
[0070] S11: Input the original hyperspectral image data to obtain the current sample point set;
[0071] S12: Delineate N neighborhood areas of different sizes for each current sample point in the current sample point set; each current sample point obtains a corresponding set of N neighborhood sample points; for the neighborhood sample points of the current sample point The set is enhanced to obtain the new sample point corresponding to the current sample point;
[0072] S13: Combining all newly added sample point data corresponding to the current sample point into an augmented data set of the current sample point, traversing the current sample point set to obtain enhanced image data;
[0073] S14: Use the original hyperspectral image data and the enhanced hyperspectral image data to train a clas...
specific Embodiment 2
[0083] Specific embodiment two, the present invention provides a small-sample hyperspectral classification method based on data enhancement, such as image 3 and Figure 4 shown.
[0084] S21: Input the current hyperspectral image data to obtain the current sample point set;
[0085] S22: For each current sample point in the current sample point set, a neighborhood area with a preset size is correspondingly defined, and each current sample point obtains a corresponding neighborhood sample point set; the neighborhood sample point set is enhanced to obtain The new sample point corresponding to the current sample point; traverse the current sample point set to get all the new sample points of the current sample point;
[0086] S23: Use the data of each newly added sample point as the second hyperspectral image data; store the second hyperspectral image data; use the second hyperspectral image data as the current hyperspectral image data of S21, iterate N times of execution step...
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