Multi-scale classification error and uncertainty modeling on categorical maps from remotely sensed data

点击翻译按钮获取中文摘要

Environmental modeling often requires inputs of detailed land cover and vegetation data at different spatial and temporal scales. Airborne and satellite remotely-sensed data play a key role in generating categorical maps such as land cover because of its capacity of collecting data over broad expanses of land. With widespread use of remote sensing and geographical information system (GIS) technologies, a great deal of earth observation data has been accumulated along with a wide range of spatial, spectral and temporal scales. These developments demand significant changes in the approach of analyzing and integrating these earth observation data. The effects of spatial, spectral and temporal resolutions on the classification accuracy of land cover and other categorical maps have received growing attention. Compared with rapidly growing data availability, there is a clear lag in the development of analysis methods and efficient error models for handling multi-scale data of increasing complexity and quantity.