Evaluation of the merging of SPOT multispectral and panchromatic data for classification of an urban environment
Two merging techniques based on the Price algorithm and the high pass filter (HPF) have been used to merge SPOT XS with PAN data to evaluate the effect of merging in classification of urban areas. The Price algorithm has been found to produce a smaller distortion of the spectral characteristics of merged data compared to the HPF algorithm. It generates accuracies similar to the original data using spectral or a combination of spectral and textural features. The gain in overall accuracy by adding one texture band over pure spectral features is higher for merged data than with the original data. Both data merging algorithms result in inferior overall and individual class accuracies compared to the original data for pure spectral as well as for a combination of spectral and texture features. The Price algorithm should be used only for those spectral bands that are highly correlated with PAN data. For the poorly correlated band, the HPF algorithm should be used; while using the HPF algorithm, it is preferable to use the cubic convolution resampler.