ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Articles | Volume I-7
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., I-7, 129–134, 2012
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., I-7, 129–134, 2012

  17 Jul 2012

17 Jul 2012


T. Hoberg, F. Rottensteiner, and C. Heipke T. Hoberg et al.
  • IPI, Institute of Photogrammetry and GeoInformation, Leibniz Universitaet Hannover, Germany

Keywords: Contextual, Multiresolution, Multitemporal, Land Cover, Classification, Conditional Random Fields

Abstract. The increasing availability of multitemporal satellite remote sensing data offers new potential for land cover analysis. By combining data acquired at different epochs it is possible both to improve the classification accuracy and to analyse land cover changes at a high frequency. A simultaneous classification of images from different epochs that is also capable of detecting changes is achieved by a new classification technique based on Conditional Random Fields (CRF). CRF provide a probabilistic classification framework including local spatial and temporal context. Although context is known to improve image analysis results, so far only little research was carried out on how to model it. Taking into account context is the main benefit of CRF in comparison to many other classification methods. Context can be already considered by the choice of features and in the design of the interaction potentials that model the dependencies of interacting sites in the CRF. In this paper, these aspects are more thoroughly investigated. The impact of the applied features on the classification result as well as different models for the spatial interaction potentials are evaluated and compared to the purely label-based Markov Random Field model.