Synthetic Aperture Radar Remote Sensing for Crop Classification

This Study suggests the approach for crop classification utilizing the Grey Level Co-occurrence Matrix feature of Synthetic Aperture Radar (SAR) countenances. The method applies the SAR Images acquired by Sentinel 1A SAR Data and extract textural face utilizing GLCM. In this study, we investigate the potential of Grey Level Co-incident Matrix (GLCM)-based nature information for gardening crop classification accompanying SAR images in Kharif and cloud weather condition. A study on Synthetic Aperture Radar (SAR) subsidiary imagery was transported in Chhattisgarh with the objective to judge the potential of various texture limits among crop. The SAR dossier were pre-processed for textural reasoning having whole angle and equal distance quantization. The results were categorized between different limits showing important variation for gardening crops for Contrast, Dissimilarity, Homogeneity, ASM, Energy, Entropy and GLCM Mean. The mathematical analysis was ruined fruit crop in addition to major kharif crop of study extent. The results shows that mean backscatter value was shortest for banana (99.12 dB) and topmost for Mango (198.26 dB) regarding contrast textural feature in VH Channel whereas mean backscatter profit in VH Channel w.r.t to energy was maximum for joker (0.60 dB) attended by papaya (0.49 dB) and guava (0.45 dB) and slightest for mango (0.44 dB). The mean backscatter value for GLCM mean textural characteristic in VH channel was shown maximum by joker (51.24 dB) followed by fruit (41.96 dB) and mango (32.98 dB). These results indicate the utility of texture facts for classification of SAR representations, specifically when acquisition of ocular images is troublesome in Kharif and cloud weather condition for crop classification. Thus GLCM feature of SAR Data resulted to be meaningful for the classification of gardening crops.

Please read full article - https://journalijpss.com/index.php/IJPSS/article/view/2961