Bayesian scale space analysis of temporal changes in satellite images

Abstract

We consider the detection of land cover changes using pairs of Landsat ETM+ satellite images. The images consist of eight spectral bands and to simplify the multidimensional change detection task, the image pair is first transformed to a one-dimensional image. When the transformation is non-linear, the true change in the images may be masked by complex noise. For example, when changes in the Normalized Difference Vegetation Index is considered, the variance of noise may not be constant over the image and methods based on image thresholding can be ineffective. To facilitate detection of change in such situations, we propose an approach that uses Bayesian statistical modeling and simulation-based inference. In order to detect both large and small scale changes, our method uses a scale space approach that employs multi-level smoothing. We demonstrate the technique using artificial test images and two pairs of real Landsat ETM+satellite images.

Keywords:

• remote sensing
• change detection
• NDVI
• Bayesian methods
• scale space
• iBSiZer

AMS Subject Classification:

• 62P12
• 62H35

Acknowledgements

We are grateful to Erkki Tomppo and Kai Mäkisara from the Finnish Forest Research Institute for the Landsat images used in the first two examples and to Miska Luoto from the Department of Geosciences and Geography of the University of Helsinki for the image pair used in the third example. Work was supported by Academy of Finland under grants nos. 122067 and 250862 (L.P.).