Polarized SAR image classification method based deep multi-example learning
A multi-instance learning and classification method technology, applied in the field of polarimetric SAR image classification based on deep multi-instance learning, can solve the problem of low image classification accuracy, and achieve the effects of improving classification accuracy, improving feature information, and enriching feature information.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0028] Reference figure 1 The specific implementation steps of the present invention are as follows:
[0029] Step 1. Input the polarization SAR image to be classified, and perform refined polarization Lee filtering on the image to obtain the polarization SAR image containing the polarization coherence matrix T and the polarization covariance matrix C, which is achieved through the following steps:
[0030] Step 1a: Set the filter window size of the SAR image to be polarized to obtain multiple mean windows, select edge templates in different directions for each mean window, and perform edge detection to obtain multiple directional filter windows: classify the polarized SAR image to be classified On the span total power image, the value of each pixel of the image is equal to the sum of the diagonal elements of the polarization covariance matrix of the pixel, and the size is set to 7×7 filter window, according to the image pixel spatial position, from left to The filter window is dec...
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