Back to Search
Start Over
SAR ATR Based on Convolutional Neural Network
- Source :
- Leida xuebao, Vol 5, Iss 3, Pp 320-325 (2016)
- Publication Year :
- 2016
- Publisher :
- China Science Publishing & Media Ltd. (CSPM), 2016.
-
Abstract
- This study presents a new method of Synthetic Aperture Radar (SAR) image target recognition based on a convolutional neural network. First, we introduce a class separability measure into the cost function to improve this network’s ability to distinguish between categories. Then, we extract SAR image features using the improved convolutional neural network and classify these features using a support vector machine. Experimental results using moving and stationary target acquisition and recognition SAR datasets prove the validity of this method.
Details
- Language :
- English, Chinese
- ISSN :
- 2095283X
- Volume :
- 5
- Issue :
- 3
- Database :
- Directory of Open Access Journals
- Journal :
- Leida xuebao
- Publication Type :
- Academic Journal
- Accession number :
- edsdoj.42827ad78ec9432faf62335de14a0a82
- Document Type :
- article
- Full Text :
- https://doi.org/10.12000/JR16037