Hyperspectral image classification method based on novel neighborhood selection constraints
A hyperspectral image and classification method technology, applied in the field of hyperspectral image classification, can solve the problem of single neighborhood information, hyperspectral image neighborhood information is not considered, and is not high enough to achieve high classification accuracy and good visual effects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0032] The technical solutions of the present invention will be described in further detail below with reference to the accompanying drawings, but the protection scope of the present invention is not limited to the following.
[0033] Such as figure 1 As shown, a hyperspectral image classification method based on a new type of neighborhood selection constraint includes the following steps:
[0034] S1. Read in hyperspectral image data.
[0035] The dimension of the read-in 3D hyperspectral data is b*L*q, and the image size is b*L, with q bands.
[0036] S2. Select training samples according to the hyperspectral data, and construct a dictionary D.
[0037] Hyperspectral data The hyperspectral data contains a total of j categories of features. A part of the pixel samples from each category are selected as training samples, and the set of these training samples is used as a dictionary D, D=[D 1 , D 2 ,...,D i ,...,D j ], where D i Represents a subset of the dictionary formed by the feature...
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