A Deep Learning Hybrid CNN Framework Approach for Vegetation Cover Mapping Using Deep Features

Vegetation cover mapping is an imperative task of monitoring the change in vegetation as it can help us meet sustenance requirements. In this study, we explore the future potential of multilayer Deep learning framework (DL) that comprises of hybrid of CNN's, for mapping vegetation cover area as DL is a congenial state-of-art algorithm for implementing image processing. This study proposes a novel DL framework exploiting hybrids of CNN's with Local binary pattern and GIST features. Every CNN is fed with disparate combination of multi-spectral Sentinel 2 satellite imagery bands (spatial resolution of 10m), texture and topographic parameters of Uttarakhand (30° 15' N, 79° 15' E) region, India. Our proposed DL framework outperformed the state-of-art algorithms with a classification accuracy of 88.43%.