Descripción
|
|
---|---|
This work proposes a new approach for change/no-change unsupervised detection by means Multi-Resolution Analysis (MRA), specifically Dual Tree Complex Wavelet Transform (DT-CWT) to extract spectral component of the two input multitemporal images. The two spectral components are then compared using the spectral ERGAS index, which have been modified for lo-cal analysis. For thresholding optimization the receiver-operating-characteristics (ROC) curve has been used and its results compared with several automatic thresholding strategies. The proposed method was compared with classical unsupervised change detection approaches. | |
Internacional
|
Si |
DOI
|
|
Edición del Libro
|
|
Editorial del Libro
|
|
ISBN
|
978-80-01-04868-9 |
Serie
|
|
Título del Libro
|
Remote Sensing and Geoinformation not only for Scientific Cooperation |
Desde página
|
247 |
Hasta página
|
254 |