V. CONCLUSION
In this paper, we carried out a study of multi-sensor satellite
image indexing. To this end, we prepared four datasets
consisting of multispectral and panchromatic images from
WoldView-2, and Synthetic Aperture Radar (SAR) images
from TerraSAR-X satellite. The indexing is carried out based
on an active learning system. A series of independent and joint
indexing by combining the features have been performed.
Through this study, we found that the indexing accuracy on
SAR images is the worst. By contrast, the joint indexing by
concatenating the features computed from each kind of image
could provide best accuracy. To conclude, the joint sensor data
enable us to discriminate more accuracy the retrieved
categories (over all investigated cities).