ABSTRACT
The fastest growth in population directly impacts the urbanization process leading to changes in the landscape and thus necessitates the study of land use/land cover. Deep learning had a significant impact on classification of tasks, particularly in the field of remote sensing image analysis. The proposed framework classifies land-use/land-cover classes by employing the characteristics of deep learning. In this work, we compared the proposed method with the traditional machine learning method for extracting dense forest, wheat, and eucalyptus. Further, we analyze the impact of optimizers like stochastic gradient descent and Adam. The proposed method with the Adam optimizer gives higher accuracy compared to other combinations.
