TY - JOUR

T1 - Conditional random fields for multitemporal and multiscale classification of optical satellite imagery

AU - Hoberg, Thorsten

AU - Rottensteiner, Franz

AU - Feitosa, Raul Queiroz

AU - Heipke, Christian

PY - 2015/2

Y1 - 2015/2

N2 - In this paper, we present a method for the multitemporal and contextual classification of georeferenced optical remote sensing images acquired at different epochs and having different geometrical resolutions. The method is based on Conditional Random Fields (CRFs) for contextual classification. The CRF model is expanded by temporal interaction terms that link neighboring epochs via transition probabilities between different classes. In order to be able to deal with data of different resolution, the class structure at different epochs may vary with the resolution. The goal of the multitemporal classification is an improved classification performance at all individual epochs, but also the detection of land-cover changes, possibly using lower resolution data. This paper also contains a comparison of the performance of different models for the interaction potentials. Results are given for two different test sites in Germany, where Ikonos, RapidEye, and Landsat images are available. Our results show that the multitemporal classification does indeed increase the overall accuracy of all epochs compared to a monotemporal classification and to a state-of-the-art multitemporal classification method, and that it is feasible to detect changes in lower resolution images.

AB - In this paper, we present a method for the multitemporal and contextual classification of georeferenced optical remote sensing images acquired at different epochs and having different geometrical resolutions. The method is based on Conditional Random Fields (CRFs) for contextual classification. The CRF model is expanded by temporal interaction terms that link neighboring epochs via transition probabilities between different classes. In order to be able to deal with data of different resolution, the class structure at different epochs may vary with the resolution. The goal of the multitemporal classification is an improved classification performance at all individual epochs, but also the detection of land-cover changes, possibly using lower resolution data. This paper also contains a comparison of the performance of different models for the interaction potentials. Results are given for two different test sites in Germany, where Ikonos, RapidEye, and Landsat images are available. Our results show that the multitemporal classification does indeed increase the overall accuracy of all epochs compared to a monotemporal classification and to a state-of-the-art multitemporal classification method, and that it is feasible to detect changes in lower resolution images.

KW - Change detection

KW - conditional random field (CRF)

KW - Markov random field (MRF)

KW - multiscale

KW - multitemporal classification

UR - http://www.scopus.com/inward/record.url?scp=84906326713&partnerID=8YFLogxK

U2 - 10.1109/TGRS.2014.2326886

DO - 10.1109/TGRS.2014.2326886

M3 - Article

AN - SCOPUS:84906326713

VL - 53

SP - 659

EP - 673

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

SN - 0196-2892

IS - 2

M1 - 6841049

ER -