arXiv subjects
Publications and source records attributed to Shahzad Gishkori.
In this paper, we propose a novel concept of cross-learning, in order to improve SAR images by learning from the camera images. We use a multi-level abstraction approach to materialise knowledge transfer between the two modalities. We also compare the performance of other possible approaches. We provide experimental results on real data to validate the proposed concept.
In this paper, we propose graph signal processing based imaging for synthetic aperture radar. We present a modified version of fused least absolute shrinkage and selection operator to cater for graph structure of the radar image. We solve the cost function via alternating direction method of multipliers. Our method provides improved denoising and resolution enhancing capabilities. It can also accommodate the compressed sensing framework quite easily. Experimental results corroborate the validity of our proposed methodology.
We propose radar image classification via pseudo-Zernike moments based sparse representations. We exploit invariance properties of pseudo-Zernike moments to augment redundancy in the sparsity representative dictionary by introducing auxiliary atoms. We employ complex radar signatures. We prove the validity of our proposed methods on the publicly available MSTAR dataset.
We present reconstruction algorithms for smooth signals with block sparsity from their compressed measurements. We tackle the issue of varying group size via group-sparse least absolute shrinkage selection operator (LASSO) as well as via latent group LASSO regularizations. We achieve smoothness in the signal via fusion. We develop low-complexity solvers for our proposed formulations through the alternating direction method of multipliers.