Small sample SAR target identification method based on graph attention network
A technology of attention and small samples, applied in the field of image processing, can solve the problems of large amount of SAR image data, large similarity of training data, overfitting, etc., and achieve low computational complexity, improved recognition performance, and fast iteration speed Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0026] The embodiments of the present invention will be further described below in conjunction with the accompanying drawings.
[0027] Reference figure 1 , The implementation steps of the present invention are as follows:
[0028] Step 1: Construct a data set for SAR small sample recognition.
[0029] 1a) Select N SAR images containing radar targets from the MSTAR data set published on the Internet as the data set, and use a mean filter with a kernel size of 4×4 to suppress coherent speckle noise on all data to obtain a denoised SAR image;
[0030] 1b) Divide the SAR image after noise reduction into labeled data and unlabeled data at a ratio of 5% to 95%.
[0031] Step two, set up an autoencoder used to extract the depth features of the SAR image.
[0032] Reference figure 2 , The self-encoder is composed of an encoder and a decoder, the input of the self-encoder is the denoised SAR image, and the output is the reconstructed SAR image;
[0033] The encoder is composed of five convolutio...
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