International Geoscience and Remote Sensing Symposium (IGARSS)
The application of remote sensing image classification to derive land covers maps is widely used, because it is a simple and fast procedure. However, these maps are many times disregarded for land use planning and management due to the difficulty to assess accuracy, as well as the lack of reference methods to tackle the problem. Presently land cover classification accuracy assessments are based solely on the used of the confusion matrix, which is a simple cross-tabulation of the mapped class against that observed in the reference data at a set of validation pixels providing a summary of commission (type I) errors and omission (type II) errors. Geostatistics framework is appropriate to model spatial variation of the classification uncertainty. Previous works proposed the use of indicator kriging to local varying means and sequential indicator simulation with prediction via collocated indicator cokriging. However, two main problems remain unsolved: the incorporation of distinct spatial error patterns for each thematic class due to its radiometric features and to take into account patch sizes contribution to uncertainty. In the present work, these two issues are address through the use of patch size weighted spatial covariance estimation in conjunction within the framework of Direct Sequential Simulation algorithm suitably modified in order to take into account patch size influence. In this work the outlined metrology is successfully applied to a Landsat classified map of an area in central Portugal. © 2014 IEEE.
Year of publication: 2014