Title :
Change Detection Based on Information Measure
Author :
Gueguen, Lionel ; Soille, Pierre ; Pesaresi, Martino
Author_Institution :
Global Security & Crisis Manage. Unit, Eur. Comm., Ispra, Italy
Abstract :
A new unsupervised change detection method for modeling nonlinear temporal dependences based on local information is proposed. A theoretical analysis is presented, demonstrating how to derive optimal parameters for automating the method. It is then validated on both simulated data and very high resolution remote sensing imagery. The results show a clear improvement in change detection using the proposed method compared to other state-of-the-art change detection techniques.
Keywords :
geophysical image processing; geophysical techniques; image resolution; remote sensing; automation method; local information analysis; nonlinear temporal model; optimal parameter; state-of-the-art change detection technique; unsupervised change detection method; very high resolution remote sensing image; Histograms; Image resolution; Measurement; Mutual information; Probability distribution; Change detection; mutual/mixed information; remotely sensed images;
Journal_Title :
Geoscience and Remote Sensing, IEEE Transactions on
DOI :
10.1109/TGRS.2011.2141999