(Article of periodic en Anglais - 2012)

Document title

A spatial-temporal modeling approach to reconstructing land-cover change trajectories from multi-temporal satellite imagery

Authors(s) and Affiliation(s)

LIU D. (1 2) ; CAI S. (1) ;
(1) Dep. of Geography, Ohio State Univ., Columbus, ETATS-UNIS
(2) Dep. of Statistics, Ohio State Univ., Columbus, ETATS-UNIS


A spatial-temporal modeling approach is developed here for reconstructing land-cover change trajectories from time series of satellite images. The change detection method represents an enhancement to the conventional post-classification comparison. The key innovation lies in the use of Markov random field theory to model spatial-temporal contextual information explicitly in the classification of time series images. When evaluated using a time series of 7 Landsat images in a case study of southeast Ohio, the spatial-temporal modeling approach yielded significantly more accurate and consistent trajectories of land-cover change than conventional non-contextual approaches. These results also highlight the utility of spatial-temporal contextual information in improving the accuracy and consistency of land-cover classifications across space and time


Article of periodic

published at : Annals of the Association of American Geographers / ISSN 0004-5608 / CODEN AAAGAK

Editor : Association of American Geographers, Washington, DC - ETATS-UNIS (1911)

Millesime : 2012, vol. 102, no6 [pp. 1329-1347]

Bibliographic references : 2 p.

Collation : 8 fig., 6 tabl.




Digital Object Identifier

Go to electronic document thanks to its DOI : doi:10.1080/00045608.2011.596357

Tous droits réservés © Prodig - Bibliographie Géographique Internationale (BGI), 2013
Refdoc record number (ud4) : 26722690 : Permanent link - XML version
Powered by Pxxo