Remotely sensed data have been widely used for environment change study in the past decades and large collections of remote sensing imagery have made it possible to analyze long-term change of environmental elements and impact of human activities. Research has been widely reported on methodology of remote sensing change detection and monitoring (e.g. Singh 1989, MacLeod and Congalton 1998, Mas 1999, Lu et al. 2004). Change detection approaches can be characterized into two broad groups, namely, bi-temporal change detection and temporal trajectory analysis (Coppin et al. 2004). The former measures land cover changes based on a 'two-epoch' timescale, i.e. The comparison between two dates. Even if land cover information sometimes is acquired for more than two epochs, the changes are still measured on the basis of pairs of dates. The latter analyses the changes based on a 'continuous' timescale, i.e. The focus of the analysis is not only on what has changed between dates, but also on the progress of the change over the period. At present, most change detection methods belong to bi-temporal change detection approach including, for example, image differencing (Weismiller et al. 1977, Maktav and Erbek 2005), vegetation index differencing (Muttitanon and Tripathi 2005), change vector analysis (CVA) (Malila, 1980, Lunetta et al. 2004), principal component analysis (PCA) (Byrne et al. 1980, Liu et al. 2004), post-classification comparison (Weismiller et al. 1977, Dewidar 2004), multi-temporal composite and classification (Zhao et al. 2004), and artificial neural network (ANN) (Dai and Khorram 1999, Liu and Lathrop Jr. 2002).
Scopus Subject Areas
- Environmental Science(all)
- Earth and Planetary Sciences(all)