Change detection based on information measure
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.
GUEGUEN Lionel;
SOILLE Pierre;
PESARESI Martino;
2011-11-08
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
JRC59639
0196-2892,
http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=05776675,
https://publications.jrc.ec.europa.eu/repository/handle/JRC59639,
10.1109/TGRS.2011.2141999,
Additional supporting files
| File name | Description | File type | |
|---|
