Partially supervised classification of multisource data

Diego Fernandez-Prieto; Olivier Arino

doi:10.1117/12.463173

Translator Disclaimer

13 March 2003 Partially supervised classification of multisource data

Diego Fernandez-Prieto, Olivier Arino

Author Affiliations +

Proceedings Volume 4885, Image and Signal Processing for Remote Sensing VIII; (2003) https://doi.org/10.1117/12.463173
Event: International Symposium on Remote Sensing, 2002, Crete, Greece

Abstract

A novel data fusion approach to partially supervised classification problems is presented, which allows a specific land-cover class of interest to be mapped by using only training samples belonging to such class. This represents a significant operational advantage in many application domains where end-users require information products for the monitoring of a specific or few land cover classes (e.g., forestry, urban monitoring) of interest. The proposed technique overcomes one of the main methodological drawbacks of this type of problems: i.e., the lack of prior knowledge on the statistics of the unknown classes present in the scene under consideration. Experiments carried out on a multisource data set demonstrate the validity of the proposed technique.

Citation Download Citation

Diego Fernandez-Prieto and Olivier Arino "Partially supervised classification of multisource data", Proc. SPIE 4885, Image and Signal Processing for Remote Sensing VIII, (13 March 2003); https://doi.org/10.1117/12.463173

ACCESS THE FULL ARTICLE