Boussad Azmedroub
ABSTRACT
Polarimetric Synthetic Aperture Radar (PolSAR) imagery classification is widely investigated, and there are a lot of proposed classifiers. The main issue in the classification of PolSAR images is the extraction of effective features that allow the preservation of the scattering mechanisms in order to give good results. In this paper we investigate the effectiveness of the textures features for polarimetric SAR images. We used for this analysis two classifiers, Feed Forward Neural Network (FNN) and the Maximum Likelihood (ML) Wishart. The textures extracted are the Gabor filters. The results show that textures add information to the polarimetric features, thus, allowing good classification results. In order to validate our experiment we used two PolSAR images RADARSAT-2, and AIRSAR C-band images of San Francisco.
- Hao Yu Bogdan M. Wilamowski. 2010. Improved Computation for LevenbergMarquardt Training. IEEE transactions on neural networks 21, 6 (june 2010). Google Scholar
Digital Library
- M. Duquenoy, J. P Ovarlez, C. Morisseau, G. Vieillard, L. Ferro-Famil, and E. Pottier. 2009. Supervised classification by neural networks using polarimetric time-frequency signatures. In IEEE International Geoscience and Remote Sensing Symposium, 2009, IGARSS 2009, Vol. 4. IV-438--IV-441.Google Scholar
- Y. Hara, R.G. Atkins, S.H. Yueh, R.T. Shin, and J.A. Kong. 1994. Application of neural networks to radar image classification. IEEE Transactions on Geoscience and Remote Sensing 32, 1 (1994), 100--109.Google ScholarCross Ref
- Anil K Jain and Farshid Farrokhnia. 1990. Unsupervised texture segmentation using Gabor filters. IEEE, 14--19.Google Scholar
- Jong-Sen Lee. 1981. Refined filtering of image noise using local statistics. Computer graphics and image processing 15, 4 (1981), 380--389.Google Scholar
- Jong-Sen Lee, Mitchell R. Grunes, and R. Kwok. 1994. Classification of multi-look polarimetric SAR imagery based on complex Wishart distribution. International Journal of Remote Sensing 15, 11 (1994), 2299--2311.Google ScholarCross Ref
- Jong-Sen Lee and Eric Pottier. 2009. Polarimetric Radar Imaging from basics to applications. Taylor & Francis Group.Google Scholar
- Eric Pottier and Joseph Saillard. 1993. Classification of earth terrain in polarimetric SAR images using neural nets modelization. In San Diego '92. International Society for Optics and Photonics. 321--332.Google ScholarCross Ref
- L.-K. Soh and C. Tsatsoulis. 1999. Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices. IEEE Transactions on Geoscience and Remote Sensing 37, 2 (March 1999), 780--795.Google ScholarCross Ref
- S. Uhlmann and S. Kiranyaz. 2013. Evaluation of classifiers for polarimetric SAR classification. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). 775--778.Google Scholar
- Perumal Vasuki and S. Mohamed Mansoor Roomi. 2013. Automatic target classification of man-made objects in synthetic aperture radar images using Gabor wavelet and neural network. Journal of Applied Remote Sensing 7, 1 (2013), 073592--073592.Google ScholarCross Ref
Recommendations
Polarimetric SAR image classification by using artificial neural network
ICWET '10: Proceedings of the International Conference and Workshop on Emerging Trends in TechnologyThe classification of various land cover features using fully polarimetric Synthetic Aperture Radar (SAR) data sets is an important application of radar remote sensing. The data acquired is over various parts of India are SIR-C L- and C-band data over ...
Speckle Reduction of Polarimetric SAR Image Based on ICA-SCS Algorithm
ISCSCT '08: Proceedings of the 2008 International Symposium on Computer Science and Computational Technology - Volume 01In this paper, a new method of sparse coding shrinkage based on independent component analysis is proposed to reduce speckle in polarimetric SAR Images. With soft-thresholding operator on polarimetric SAR Image, this method reduces speckle effectively ...
Colorization for Polarimetric SAR Image Based on Scattering Mechanisms
CISP '08: Proceedings of the 2008 Congress on Image and Signal Processing, Vol. 4 - Volume 04Polarimetric synthetic aperture radar (POLSAR) images are widely used for aerial and spatial image applications, such as terrain classification, target detection, etc. However, only monochrome gray images can be derived from SAR data due to the imaging ...
Comments