Real-Time Super-Resolution ISAR Imaging Using Unsupervised Learning
| Autor: | Xuejun Huang, Jinshan Ding, Zhong Xu |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
Ground truth
Computer science business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Process (computing) Iterative reconstruction Geotechnical Engineering and Engineering Geology Superresolution Convolutional neural network Inverse synthetic aperture radar Compressed sensing Unsupervised learning Computer vision Artificial intelligence Electrical and Electronic Engineering business |
| Zdroj: | IEEE Geoscience and Remote Sensing Letters. 19:1-5 |
| ISSN: | 1558-0571 1545-598X |
| DOI: | 10.1109/lgrs.2021.3128525 |
| Popis: | Compressive sensing (CS) enables high-resolution ISAR imaging with limited measurements. However, these methods reconstruct images via iterative optimization, resulting in a high computational load. Recently, convolutional neural networks (CNNs) have been used to perform superresolution ISAR imaging in real time, where high-resolution images are necessarily used as ground truth. However, the desired high-resolution images are not reliable in practice. This letter presents an unsupervised CNN-based framework for superresolution ISAR imaging. The well-trained CNN can directly produce high-resolution ISAR images in real time. More-over, the network is trained in an unsupervised manner, which is suitable for practical applications. Furthermore, a pseudo l0-norm has been used as the sparse constraint for the exact image reconstruction. The proposed approach has been used to process the real ISAR data, and the experimental results are convincing. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|