Optimized Wishart Network for an Efficient Classification of Multifrequency PolSAR Data

High-resolution wide-area images are required in the diverse field of research ranging from urban planning and disaster prediction to agriculture and geology. Sometimes the image is taken under harsh weather conditions or at night time. Current optical remote sensing technology does not have the capability to acquire images in such conditions. Synthetic aperture radar (SAR) uses microwave signal which has a long-range propagation characteristic that allows us to capture images in difficult weather conditions. In addition to this, some polarimetric SAR (PolSAR) systems are also capable of capturing images using multifrequency bands simultaneously resulting into a multitude of information in comparison to the optical images. In this letter, we propose a single-hidden layer optimized Wishart network (OWN) and extended OWN for classification of the single-frequency and multifrequancy PolSAR data, respectively. Performance evaluation is conducted on a single-frequency as well as multifrequency SAR data obtained by Airborne Synthetic Aperture Radar. We observed that for combining multiple band information, proposed single-hidden layer network outperforms deep learning-based architecture involving multiple hidden layers.

[1]  Dan Zhang,et al.  Stacked Sparse Autoencoder in PolSAR Data Classification Using Local Spatial Information , 2016, IEEE Geoscience and Remote Sensing Letters.

[2]  J. S. Lee,et al.  Classification of multi-look polarimetric SAR data based on complex Wishart distribution , 1992, [Proceedings] NTC-92: National Telesystems Conference.

[3]  Si-Wei Chen,et al.  PolSAR Image Classification Using Polarimetric-Feature-Driven Deep Convolutional Neural Network , 2018, IEEE Geoscience and Remote Sensing Letters.

[4]  Jin Zhao,et al.  POLSAR Image Classification via Wishart-AE Model or Wishart-CAE Model , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[5]  Jong-Sen Lee,et al.  Intensity and phase statistics of multilook polarimetric and interferometric SAR imagery , 1994, IEEE Trans. Geosci. Remote. Sens..

[6]  Biao Hou,et al.  Classification of Polarimetric SAR Images Using Multilayer Autoencoders and Superpixels , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[7]  Simonetta Paloscia,et al.  The potential of multifrequency polarimetric SAR in assessing agricultural and arboreous biomass , 1997, IEEE Trans. Geosci. Remote. Sens..

[8]  Jian Yang,et al.  Land Cover Classification for Polarimetric SAR Images Based on Mixture Models , 2014, Remote. Sens..

[9]  Haipeng Wang,et al.  Complex-Valued Convolutional Neural Network and Its Application in Polarimetric SAR Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Kun-Shan Chen,et al.  Classification of multifrequency polarimetric SAR imagery using a dynamic learning neural network , 1996, IEEE Trans. Geosci. Remote. Sens..

[11]  Licheng Jiao,et al.  Wishart Deep Stacking Network for Fast POLSAR Image Classification. , 2016, IEEE transactions on image processing : a publication of the IEEE Signal Processing Society.

[12]  Avik Bhattacharya,et al.  Tensorization of Multifrequency PolSAR Data for Classification Using an Autoencoder Network , 2018, IEEE Geoscience and Remote Sensing Letters.

[13]  Yu Zhou,et al.  Polarimetric SAR Image Classification Using Deep Convolutional Neural Networks , 2016, IEEE Geoscience and Remote Sensing Letters.