The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Download
Citation
Articles | Volume XL-8
https://doi.org/10.5194/isprsarchives-XL-8-781-2014
https://doi.org/10.5194/isprsarchives-XL-8-781-2014
28 Nov 2014
 | 28 Nov 2014

Entropy based determination of optimal principal components of Airborne Prism Experiment (APEX) imaging spectrometer data for improved land cover classification

A. Kallepalli, A. Kumar, and K. Khoshelham

Keywords: High resolution data, hyper spectral, land cover, classification, feature extraction

Abstract. Hyperspectral data finds applications in the domain of remote sensing. However, with the increase in amounts of information and advantages associated, come the "curse" of dimensionality and additional computational load. The question most often remains as to which subset of the data best represents the information in the imagery. The present work is an attempt to establish entropy, a statistical measure for quantifying uncertainty, as a formidable measure for determining the optimal number of principal components (PCs) for improved identification of land cover classes. Feature extraction from the Airborne Prism EXperiment (APEX) data was achieved utilizing Principal Component Analysis (PCA). However, determination of optimal number of PCs is vital as addition of computational load to the classification algorithm with no significant improvement in accuracy can be avoided. Considering the soft classification approach applied in this work, entropy results are to be analyzed. Comparison of these entropy measures with traditional accuracy assessment of the corresponding „hardened‟ outputs showed results in the affirmative of the objective. The present work concentrates on entropy being utilized for optimal feature extraction for pre-processing before further analysis, rather than the analysis of accuracy obtained from principal component analysis and possibilistic c-means classification. Results show that 7 PCs of the APEX dataset would be the optimal choice, as they show lower entropy and higher accuracy, along with better identification compared to other combinations while utilizing the APEX dataset.