A Framework for Automatic and Unsupervised Detection of Multiple Changes in Multitemporal Images

• Published in: IEEE transactions on geoscience and remote sensing Vol. 50; no. 6; pp. 2196 - 2212
• Main Authors: Bovolo, Francesca, Marchesi, S., Bruzzone, L.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.06.2012; Institute of Electrical and Electronics Engineers
• Subjects: Accuracy; Applied geophysics; Bayes decision rule; change detection (CD); change vector analysis (CVA); Data mining; Earth sciences; Earth, ocean, space; Exact sciences and technology; Feature extraction; Geologic measurements; Image coding; Internal geophysics; low-dimensional representation; multiple changes; multitemporal images; Remote sensing; thresholding procedure; Vectors; ground truth; detection; multispectral remote sensing; multitemporal images; remote sensing; thresholding procedure; Bayes decision rule; change detection (CD); low-dimensional representation; channels; solution; standard samples; change vector analysis (CVA); multiple changes; strategy; frame structure

The detection of multiple changes (i.e., different kinds of change) in multitemporal remote sensing images is a complex problem. When multispectral images having B spectral bands are considered, an effective solution to this problem is to exploit all available spectral channels in the framework of s...