A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Polarimetric SAR Image Filtering Based on Patch Ordering and Simultaneous Sparse Coding
In this paper, a transform-domain filtering method is proposed for polarimetric synthetic aperture radar (POLSAR) images via patch ordering and simultaneous sparse coding (SSC). First of all, we establish a signal-dependent additive noise model for the POLSAR covariance matrix and derive the noise variance for each element of the matrix based on the complex Wishart distribution. Next, we propose an extended patch ordering algorithm for POLSAR images by extracting sliding patches and organizing them in a regular way. Then, the ordered patches are filtered by SSC, for the purpose of which we develop a new weighted simultaneous orthogonal matching pursuit algorithm by embedding the signal-dependent noise model of the POLSAR data. Finally, the filtering result is reconstructed from the filtered patches via inverse permutation and subimage averaging. Experimental results with both simulated and real POLSAR images demonstrate that the proposed method can achieve state-of-the-art filtering performance.
Polarimetric SAR Image Filtering Based on Patch Ordering and Simultaneous Sparse Coding
In this paper, a transform-domain filtering method is proposed for polarimetric synthetic aperture radar (POLSAR) images via patch ordering and simultaneous sparse coding (SSC). First of all, we establish a signal-dependent additive noise model for the POLSAR covariance matrix and derive the noise variance for each element of the matrix based on the complex Wishart distribution. Next, we propose an extended patch ordering algorithm for POLSAR images by extracting sliding patches and organizing them in a regular way. Then, the ordered patches are filtered by SSC, for the purpose of which we develop a new weighted simultaneous orthogonal matching pursuit algorithm by embedding the signal-dependent noise model of the POLSAR data. Finally, the filtering result is reconstructed from the filtered patches via inverse permutation and subimage averaging. Experimental results with both simulated and real POLSAR images demonstrate that the proposed method can achieve state-of-the-art filtering performance.
Polarimetric SAR Image Filtering Based on Patch Ordering and Simultaneous Sparse Coding
Xu, Bin (author) / Cui, Yi / Zuo, Bin / Yang, Jian / Song, Jianshe
2016
Article (Journal)
English
Local classification TIB:
770/3710/5670
BKL:
38.03
Methoden und Techniken der Geowissenschaften
/
74.41
Luftaufnahmen, Photogrammetrie
Unsupervised Classification of Polarimetric SAR Images via Riemannian Sparse Coding
| Online Contents | 2017
Structured Sparse Coding-Based Hyperspectral Imagery Denoising With Intracluster Filtering
| Online Contents | 2017
Adaptive-Window Polarimetric SAR Image Speckle Filtering Based on a Homogeneity Measurement
| Online Contents | 2015
Mean-shift-based speckle filtering of polarimetric SAR data
| Online Contents | 2014
Mean-Shift-Based Speckle Filtering of Polarimetric SAR Data
| Online Contents | 2014