Hyperspectral image classification via shape-adaptive deep learning

Abstract

Hyperspectral image(HSI) Classification is one of the most prevalent issue in remote sensing area. Recently, application of deep learning in HSI classification has emerged. However, merging spatial features with spectral properties in deep learning is a pervasive problem. This paper presents, a discriminative spatial updated deep belief network (SDBN) which effectively utilizes spatial information within spectrally identical contiguous pixels for HSI classification. In the proposed approach, HSI is first segmented into adaptive boundary adjustment based spatially similar regions with similar spectral features, following which an object-level feature extraction and classification is undertaken using deep belief network (DBN) based decision fusion approach that incorporate spatial-segmented contextual and spectral information into a DBN framework for effective spectral-spatial HSI classification. Moreover, for improved accuracy, band preference/correlation based feature selection approach is used to select the most informative bands without compromising the original content in HSI. Usage of local contextual features and spectral similarity from adaptive boundary adjustment based approach, and integration of spatial and spectral features into DBN results into improved accuracy of the final HSI classification. Experimental results on well known hyperspectral data indicates the classification accuracy of the proposed method over several existing techniques.