TY - GEN

T1 - Efficient Incorporation of Markov Random Fields in Change Detection

A1 - Aanæs,Henrik

A1 - Nielsen,Allan Aasbjerg

A1 - Carstensen,Jens Michael

A1 - Larsen,Rasmus

A1 - Ersbøll,Bjarne Kjær

AU - Aanæs,Henrik

AU - Nielsen,Allan Aasbjerg

AU - Carstensen,Jens Michael

AU - Larsen,Rasmus

AU - Ersbøll,Bjarne Kjær

PB - IEEE

PY - 2009

Y1 - 2009

N2 - Many change detection algorithms work by calculating the probability of change on a pixel-wise basis. This is a disadvantage since one is usually looking for regions of change, and such information is not used in pixel-wise classification - per definition. This issue becomes apparent in the face of noise, implying that the pixel-wise classifier is also noisy. There is thus a need for incorporating local homogeneity constraints into such a change detection framework. For this modelling task Markov Random Fields are suitable. Markov Random Fields have, however, previously been plagued by lack of efficient optimization methods or numerical solvers. We here address the issue of efficient incorporation of local homogeneity constraints into change detection algorithms. We do this by exploiting recent advances in graph based algorithms for Markov Random Fields. This is combined with an IR-MAD change detector, and demonstrated on real data with good results.

AB - Many change detection algorithms work by calculating the probability of change on a pixel-wise basis. This is a disadvantage since one is usually looking for regions of change, and such information is not used in pixel-wise classification - per definition. This issue becomes apparent in the face of noise, implying that the pixel-wise classifier is also noisy. There is thus a need for incorporating local homogeneity constraints into such a change detection framework. For this modelling task Markov Random Fields are suitable. Markov Random Fields have, however, previously been plagued by lack of efficient optimization methods or numerical solvers. We here address the issue of efficient incorporation of local homogeneity constraints into change detection algorithms. We do this by exploiting recent advances in graph based algorithms for Markov Random Fields. This is combined with an IR-MAD change detector, and demonstrated on real data with good results.

KW - Markov Random Fields

KW - IR-MAD

KW - Homogeneity Constraints

KW - Graph Based Algorithms

KW - Change Detection

U2 - 10.1109/IGARSS.2009.5417856

DO - 10.1109/IGARSS.2009.5417856

SN - 978-1-4244-3394-0

VL - 3

BT - IEEE International Geoscience and remote sensing symposium

T2 - IEEE International Geoscience and remote sensing symposium

ER -