Research findings clearly indicate that the double-threshold strategy improves the overall accuracy from 93.1% to 95.9%.It is worth mentioning that, as change detection is an important step in data updating, some methods used spectral-based methods such as the Iterative Principal Components Analysis(IPCA) to determine temporal distance in feature space and combine it with a Bayesian decision rule to determine the presence of change (Spitzer et al., 2001). Clifton (2003)describes training neural networks to learn expected changes between images and to then identify pixel changes which do not
match what is “expected”