Polarization SAR terrain classification method based on deep learning and distance metric learning
A metric learning and deep learning technology, applied in the field of image classification and image processing, can solve the problems of high time complexity, limited classification accuracy, slow processing speed, etc., to achieve low time complexity, overcome low classification accuracy, improve classification The effect of precision
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0041] The present invention will be further described below in conjunction with the drawings.
[0042] Reference attached figure 1 The specific steps of the present invention are as follows:
[0043] Step 1. Input the polarization SAR image to be classified.
[0044] Step 2. Filtering.
[0045] The Lee filter method with a filter window size of 7×7 is used to filter the polarized SAR image to be classified, remove the coherent speckle noise, and obtain the filtered polarized SAR image.
[0046] Step 3. Extract features.
[0047] (1) Calculate the two scattering parameters of scattering entropy and scattering angle;
[0048] The first step is to calculate the scattering entropy of the polarized SAR image according to the following formula:
[0049] H = X i = 1 3 - P i log 3 ( P i )
[0050] Among them, H represents the scattering entropy of the polarized SAR image, the value range of H is: 0≤H≤1, Σ represents the summation operation, i represe...
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