Title :
Partially-supervised updating of land-cover maps: A P2S2VM technique and a circular validation strategy
Author :
Marconcini, Mattia ; Bruzzone, Lorenzo
Author_Institution :
Trento Univ., Trento
Abstract :
In this paper, we address automatic updating of land- cover maps by using multitemporal images without a complete knowledge of training data. In particular, two main novel contributions are proposed: a progressive partially-supervised support vector machine (P2S2VM) technique that extends the SVM method to the partially-supervised classification framework; ii) a circular accuracy assessment strategy for the validation of the learning of the classifier when no labeled test samples are available. Experimental results obtained on a multitemporal and multispectral data set confirmed the effectiveness and the reliability of both the proposed P2S2VM technique and the related circular validation strategy.
Keywords :
geophysical signal processing; image classification; remote sensing; support vector machines; P2S2VM technique; automatic updating; circular validation strategy; land-cover map; multitemporal images; partially-supervised classification framework; progressive partially-supervised support vector machine; Communications technology; Costs; Employment; Iterative algorithms; Machine learning; Remote sensing; Support vector machine classification; Support vector machines; Testing; Training data; accuracy assessment; multitemporal classification; partially-supervised classification; support vector machines; validation strategy;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 2007. IGARSS 2007. IEEE International
Conference_Location :
Barcelona
Print_ISBN :
978-1-4244-1211-2
Electronic_ISBN :
978-1-4244-1212-9
DOI :
10.1109/IGARSS.2007.4422988
