A Novel Multispectral, Panchromatic and SAR Data Fusion for Land Classification

Multisensor data fusion is addressed in this article for land classification purposes in a semiarid environment. A novel algorithm based on multispectral, panchromatic and synthetic aperture radar (SAR) data is here presented. The proposed multisensory data fusion approach relies on the generalized intensity-hue-saturation (G-IHS) transform and the À trous wavelet transform (ATWT). The fusion product is obtained by modulating the high features details of the panchromatic ATWT with the SAR texture and by replacing the high-pass details of the G-IHS Intensity component with this panchromatic-SAR modulation. After the fusion product is derived, a classification is performed by using a standard maximum likelihood classifier. The proposed algorithm is tested over a meaningful case study acquired over the Maspalomas Special Natural Reserve (Spain) and processing data from WorldView-2 (for both multispectral and panchromatic channels) and TerraSAR-X (for the SAR channel) missions. Results show a fine preservation of the spectral information contained in each multispectral band. Sharpened details are observed over built-up areas and a smoothing texture is perceived over homogeneous areas (lakes, sea, bare soil, and roads) due to the SAR-panchromatic modulation. This leads to a better overall classification accuracy of the fused image compared to outcomes obtained with a single sensor, resulting 7% and 2% more accurate than multispectral and pan-sharpening classification, respectively.