Adaptive Probabilistic Models of Wavelet Packets for the Analysis and Segmentation of Textured Remote Sensing Images

Brady, K.; Jermyn, I.H.; Zerubia, J.

Abstract

Remote sensing imagery plays an important role in many fields. It has become an invaluable tool for diverse applications ranging from cartography to ecosystem management. In many of the images processed in these types of applications, semantic entities in the scene are correlated with textures in the image. In this paper, we propose a new method of analysing such textures based on adaptive probabilistic models of wavelet packets. Our approach adapts to the principal periodicities present in the textures, and can capture long-range correlations while preserving the independence of the wavelet packet coefficients. This technique has been applied to several remote sensing images, the results of which are presented.

Citation

Brady, K., Jermyn, I., & Zerubia, J. (2003). Adaptive Probabilistic Models of Wavelet Packets for the Analysis and Segmentation of Textured Remote Sensing Images. In R. Harvey, & A. Bangham (Eds.), Proceedings of the British Machine Conference 2003 (59.1-59.10). https://doi.org/10.5244/c.17.59

• Conference Name: British Machine Vision Conference (BMVC) 2003
• Conference Location: Norwich
• Publication Date: Sep 1, 2003
• Deposit Date: Aug 12, 2011
• Publicly Available Date: May 11, 2016
• Pages: 59.1-59.10
• Book Title: Proceedings of the British Machine Conference 2003.
• DOI: https://doi.org/10.5244/c.17.59
• Public URL: https://durham-repository.worktribe.com/output/1694263