A hierarchical approach to Compact Airborne Spectrographic Imager (CASI) high-resolution image classification of Little Miami River Watershed for environmental modelling

摘要

Compact Airborne Spectrographic Imager (CASI) hyperspectral imagery was acquired over the Little Miami River Watershed in Ohio, USA, which was one of the largest hyperspectral image acquisitions. A hierarchical approach was employed using two different classification algorithms: 'image object segmentation' for level 1 and 'spectral angle mapper' (SAM) for level 2. This classification scheme was developed to overcome the spectral inseparability of urban and rural features and to deal with radiometric distortions due to cross-track illumination. The land-use/land-cover (LULC) classes were urban/built, corn, soya bean, wheat, for-est, dry herbaceous, grass, lentic, Lotic, urban barren, rural barren and unclassified. The final phase of processing was completed after an extensive quality assur-ance and quality control (QA/QC) phase with 902 points. The overall accuracy was 83.9%. The data set was made available for public research and application; certainly, this product represents an improvement over more commonly utilized, coarser spatial resolution data sets such as National Land Cover Data (NLCD).