A Method of Polarimetric Synthetic Aperture Radar Image Classification Based on Sparse Representation

Hongfu Wang, Xiaorong Xue

Abstract


Sparse representation-based techniques have shown great potential for pattern recognition problems. Therefore, on the basis of the sparse characteristics of the features for PolSAR image classification, a supervised PolSAR image classification method based on sparse representation is proposed in this paper.   It works by projecting the feature vector of the pending pixel onto a subset of training vectors from dictionary and then obtains the corresponding optimal coefficients as well as the residual error with respect to each atom. Then, the residual errors of the pending pixel with respect to each atom are evaluated and considered as the criteria for classification, namely, the ultimate class can be obtained according to the atoms with the least residual error. The verified experiment is implemented using Danish EMISAR L-band fully PolSAR data of Foulum Area(DK) to validate the performance of the proposed classification method.The preliminary experimental results confirm that the proposed method outputs an excellent result and moreover the classification process is simpler and less time consuming.


Keywords


PolSAR; sparse representation; radar image classification; feature extraction

Full Text:

PDF


DOI: http://dx.doi.org/10.12928/telkomnika.v14i3A.4415

Article Metrics

Abstract view : 39 times
PDF - 79 times

Refbacks

  • There are currently no refbacks.


Copyright (c) 2016 Universitas Ahmad Dahlan

TELKOMNIKA Telecommunication, Computing, Electronics and Control
ISSN: 1693-6930, e-ISSN: 2302-9293
Universitas Ahmad Dahlan, 4th Campus, 9th Floor, LPPI Room
Jl. Ringroad Selatan, Kragilan, Tamanan, Banguntapan, Bantul, Yogyakarta, Indonesia 55191
Phone: +62 (274) 563515, 511830, 379418, 371120 ext. 4902, Fax: +62 274 564604

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

View TELKOMNIKA Stats