Mapping land cover change in the Taita Hills, Kenya, utilizing multi-scale segmentation and object-oriented classification of SPOT imagery

In pressured environmentally sensitive and ecologically important tropical areas, such as the Taita Hills in Kenya, there is a continuing need for accurate up-to-date and historical land cover mapping that can be used in change detection studies and for developing sustainable land use policies. However, traditional classification techniques based solely on the spectral response of individual pixels achieve only limited success in complex heterogeneous tropical environments. In an attempt to improve on this situation, multispectral SPOT data from 1987, 1992 and 2003 was subject to an object-oriented classification approach to identify 12 land use/land cover classes derived using the FAO LCCS protocol. Results were compared with the standard maximum-likelihood technique. The derived maps were used to identify major landscape changes occurring in the Taita Hills over the period 1987 to 2003.