Change detection by classification of a multi-temporal image

Keeping track of changes in our environment is an important application of remote sensing. To express those changes in terms or thematic classes can be done by comparing classifications of different dates, which, however, has the disadvantage that classification errors and uncertainties are accumulated. Moreover, spectral properties of classes in a dynamic environment may be different from those in a stable situation. This paper elaborates on the statistical classification of multi-temporal data sets, using a set of thematic classes that includes class-transitions. To handle the increased complexity of the classification, refined probability estimates are presented, which pertain to image regions rather than to the entire image. The required subdivision of the area could be defined by ancillary data in a geographic information system, but can also be obtained by multi-temporal image segmentation. A case study is presented where land-cover is monitored over an 11-years period in an area in Brazil with drastic deforestation.