Abstract

The increasing wealth of remote sensing images has led to unprecedented opportunities to study the world. There are, however, some methodological complications connected with the classification of land use. Land use often takes on the physical expression of a complex combination of land cover. This combination is hard to extract using per-pixel based classification methods because of the heterogeneity and complexity of its spectral and conceptual dimensions.

Michael M Nielsen’s research explores the use of two novel methods for the classification of remotely sensed images: Spatial Relational Post-Classification and Window Independent Context Segmentation. The aim is to investigate the potential of classification methods based on spatial context to infer specific types of land use from remote sensing data. Focusing on case studies in rural and urban areas, the results show how the use of spatial context can lead to the extraction of information of interest for the social sciences in general and human geography in particular, pointing towards a methodology that can capture additional aspects than the purely (bio)physical.

Researcher

Michael Meinild Nielsen

Publications

  • Nielsen, Michael Meinild, Heurich, Marco, Malmberg, Bo and Brun, Anders (2014), Automatic mapping of standing dead trees after an insect outbreak using the Window Independent Context Segmentation Method. Journal of Forestry, DOI: 10.5849/jof.13-050.
  • Nielsen, Michael Meinild and Ahlqvist, Ola (2014), Classification of different urban categories corresponding to the strategic spatial level of urban planning and management using a SPOT4 scene. Journal of Spatial Science. DOI: 10.1080/14498596.2014.943309.
  • Nielsen, Michael Meinild (2014), Inferring Land Use from Remote Sensing Imagery: A context-based approach. Department of Human Geography, Stockholm University, Doctoral Thesis.
  • Nielsen, Michael Meinild and Hennerdal, Pontus (2014), MAUPing Workplace Clusters. Growth and Change 45(2), 211-221. DOI: 10.1111/grow.12044.
  • Wästfelt, Anders, Tegenu, Tsegaye, Nielsen, Michael M and Malmberg, Bo (2012), Qualitative satellite image analysis: Mapping spatial distribution of farming types in Ethiopia. Applied Geography 32(2), 465-476. DOI: 10.1016/j.apgeog.2011.04.001.
  • Ahlqvist, Ola, Wästfelt, Anders and Nielsen, Michael (2012), Formalized interpretation of compound land use objects - Mapping historical summer farms from a single satellite image. Journal of Land Use Science 7(1), 89-107. DOI: 10.1080/1747423X.2010.537787.
  • Nielsen, Michael Meinild (2011), Extraction of different urban area categories from satellite images using Window Independent Context Segmentation. In: Stilla, U., Gamba, P., Juergens, C. and Maktav, D. (Eds.), Joint Urban Remote Sensing Event Munich, Germany, April 11-13, 2011.
  • Wästfelt, Anders, Jansson, Johanna, Arnberg, Wolter, Moström, Jerker and Nielsen, Michael (2007), Fjärranalys i kulturmiljövårdens tjänst. Länsstyrelsen i Dalarnas län, Falun.