Semi-supervised multi-spectral remote sensing image segmentation method based on spectral clustering
A technology of remote sensing image and spectral clustering algorithm, which is applied in the preprocessing of multispectral remote sensing images and the segmentation of multispectral remote sensing images. The effect is good, the classification accuracy is improved, and the regional consistency is good.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0041] refer to figure 1 , the specific implementation steps of the present invention are as follows:
[0042] Step 1: Extract input image features.
[0043] Each pixel in the input image is represented by a feature vector to obtain an image feature set, and the feature vector is the gray value of each band of the input image.
[0044] Step 2: Randomly uniformly sample N unlabeled points and M labeled points in the input image.
[0045] For a multispectral remote sensing image with S pixels, a set of N unlabeled points and M labeled points are randomly and uniformly sampled Q = { x i } i = 1 n , n=N+M, where M labeled points, it is in the set of labeled points, select the set of points of each category with the same label, and randomly select M / in each set k points, k is the number of cat...
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