Projects per year
In this paper, we propose a novel concept of crosslearning in order to improve synthetic aperture radar (SAR) images by learning from the camera images, in the manifold domain. We present multi-level abstraction approaches to materialise knowledge transfer between these two very different modalities (i.e., the radar and the camera), namely, a canonical correlation analysis (CCA) based approach and a manifold alignment based approach. We provide experimental results on real data, along with qualitative as well as quantitative analyses, to validate the proposed methodologies.
|Number of pages||1|
|Journal||IEEE Transactions on Aerospace and Electronic Systems|
|Early online date||26 Jan 2021|
|Publication status||E-pub ahead of print - 26 Jan 2021|
FingerprintDive into the research topics of 'Improved SAR Imaging Via Cross-Learning from Camera Images'. Together they form a unique fingerprint.
- 1 Finished
14/12/15 → 31/01/20