Object-oriented oil spill contamination mapping in west siberia with quickbird data

Abstract

The work presented is part of the OSCaR pilot study (Oil Spill Contamination and mapping in Russia) and is co-financed by the International Office of the Federal Ministry of Education and Research (BMBF) Germany as part of the Core-to-Core activities on “The Symptoms of Environmental Change in the Siberian Permafrost Region” with the Japan Society of the Promotion of Science (JSPS). This paper presents concepts for an object-based mapping and classification system for terrestrial oil spill pollution in West-Siberia using Quickbird data. An object oriented classification system is created to map contaminated soils and vegetation using spectral information, shape and context information. Due to the limited spectral resolution of Quickbird data context information is used as an additional feature. The distance to industrial land use and infrastructure objects is utilized to increase the classification accuracy. Validation of the results is done with field data from the Russian partners at the Yugra State University in Khanty-Mansiyskiy.