In this paper, detection of land-cover/land-use transitions by using multitemporal remote-sensing images is addressed. An iterative approach based on a compound classification of multitemporal images is proposed. In particular, a technique to estimate iteratively the probabilities of transitions among classes is presented. The effectiveness of the proposed approach is confirmed by experimental results carried out on multitemporal remote-sensing images acquired by the Thematic Mapper of Landsat over an agricultural area.
Scheda prodotto non validato
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo