Multi-spectrum data supervised classification method based on relevant linear information entropy
A supervised classification and linear correlation technology, applied in the field of remote sensing data interpretation, to achieve accurate classification results and efficient calculations
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0031] Specific implementation manner one: such as figure 1 As shown, the method for supervised classification of multispectral data combined with linear correlation information entropy provided by this embodiment is divided into three steps, and the specific steps are as follows:
[0032] Step 1: After manual sampling, the training sample set required for supervised classification is automatically selected.
[0033] 1) For captured multispectral remote sensing images Among them, Row and Column represent the width and length of the multi-spectral remote sensing image, and B represents the number of bands of the multi-spectral remote sensing image. The image analyst selects training samples according to the sampler of F×F size. In order to ensure that the subsequent screening work can be carried out, F ≥2, that is, F can be selected once 2 Pixel training sample, using vector P m , M=1,..., F 2 To indicate that each P m The dimensionality of is equal to B, which represents the band i...
Example Embodiment
[0070] Specific implementation manner 2: This implementation manner selects a standard multispectral image data, FLCl data set. The data is airborne 12-band multispectral data taken in June 1966 in an area in the southern tippecanoe county, Indiana, USA, and the ground truth reference map was given by relevant scientific researchers on the field survey. Therefore, the data set is used for experiments. Actually evaluate the classification accuracy of the classifier algorithm. The configuration of the computer used in the experiment is as follows: Intel i32.3GHz processor, 4G memory.
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap