Enhancing land cover classification for multispectral images using hybrid polarimetry SAR data

Abstract

ABSTRACT The recent development of hybrid polarimetry synthetic aperture radar (SAR) data with decomposition techniques has improved land cover mapping. The generation of land cover maps using land cover classifications of different scenarios was carried out for Theni district, Tamil Nadu, India using optical and hybrid polarimetry SAR data. The present study focuses on evaluating the capability and contribution of hybrid decomposition techniques from Radar Imaging Satellite-1 (RISAT-1) data to improve the optical image classification accuracy. Hybrid decomposition techniques such as m-delta (m-δ), m-chi (m-χ) and m-alpha (m-α) were extracted using Stokes parameters from circular fine resolution stripmap-1 (cFRS-1) mode of RISAT-1 data. Grey level co-occurrence matrix (GLCM) textural bands were extracted from backscattering images of RISAT-1 and spectral bands of linear imaging self scanning sensor – IV (LISS-IV) image. The hybrid decomposition parameters were used to improve the classification accuracies of SAR and optical images and compared with GLCM textural bands. Support vector machine (SVM) classifier was performed for different scenarios and accuracy assessment was evaluated for all the classified images using confusion matrix with help of reference data. The study observed that the RISAT-1 derived products provided reasonable classification accuracy (54%) and also provided better results when added to spectral bands of LISS-IV (74%). The mean and dissimilarity of GLCM textural bands provided best classification, when added individually with RISAT-1 (66%) and LISS-IV (82%), and combined with RISAT-1 and LISS-IV (80%). The results indicate that the optical sensor performs better for the classification of water bodies, fallow land and settlement, however, plantation and rice crops are better classified when combined with SAR hybrid decomposition parameters. The study also observed that GLCM textural bands may change the pixel values based on the window size. The changed pixel values contributed to improving the classification accuracy by 15%. The selected classification and processing methods resulted in reasonable accuracy in land cover mapping in a hilly area with intermittent plains.