Temporal analysis of multisensor data for forest change detection using hidden Markov models

Remote sensing plays a key role in monitoring the quality and coverage of the tropical forests, and for early warning of illegal logging and forest degradation. We propose a hidden Markov model based framework for analyzing multi-source time series of remote sensing images of tropical forests with the aim of detecting changes in the spatial coverage of the forest. Multi-source is supported by the hidden Markov model by applying specific data distributions for each source. The proposed methodology is demonstrated on a time series of Landsat TM and Radarsat-2 quad-pol images covering tropical forest in Tanzania. The results are evaluated by visual inspection of Landsat 5 TM images.

[1]  Torbjørn Eltoft,et al.  Application of the Matrix-Variate Mellin Transform to Analysis of Polarimetric Radar Images , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[2]  L. Aurdal,et al.  Use of hidden Markov models and phenology for multitemporal satellite image classification: applications to mountain vegetation classification , 2005, International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, 2005..

[3]  Nicolas Viovy,et al.  Hidden Markov models applied to vegetation dynamics analysis using satellite remote sensing , 1994, IEEE Trans. Geosci. Remote. Sens..

[4]  Arnt-Børre Salberg.  Retraining maximum likelihood classifiers using a low-rank model , 2011, 2011 IEEE International Geoscience and Remote Sensing Symposium.

[5]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[6]  Arnt-Børre Salberg,et al.  Temporal analysis of forest cover using hidden Markov models , 2011, 2011 IEEE International Geoscience and Remote Sensing Symposium.