Cartographic Elements Extraction using High Resolution Remote Sensing Imagery and XML Modeling

Erick Lopez-Ornelas (1) , Florence Sèdes (2, 3)

1 UAM - Universidad Autónoma Metropolitana [Mexico]
2 IRIT-SIG - Systèmes d’Informations Généralisées
3 UT3 - Université Toulouse III - Paul Sabatier

At the present time, the remote sensing community will have to deal with new data type; very high spatial resolution and IKONOS and Quickbird data give an excellent reference of them. For some topics that are directly implied like environment or urban areas analysis, these new data will be very important. Indeed, the arrival of these images enables a new capability and the study of a range of non-observable objects until now. Using high resolution imagery should make it possible to detect man-made features such as buildings, rivers or roads in an easier way than conventional data. This research presents and proposes an automatic system of cartographic elements extraction from space images, using very high spatial resolution images. This system can be adapted to other types of remote sensing images. This research work is focussed on the extraction of four types of cartographic elements: water areas, urban areas, wooded areas and linear features such as roads or railways. Each type of cartographic element is extracted detecting its own characteristics, using image analysis, applying a segmentation process and knowledge extraction.

Mots clés: Image resolution; Remote sensing; XML; Spatial resolution; Data mining; Urban areas; Roads; Data analysis; Computer vision; Rivers

Domaines: Réseaux sociaux et d'information [cs.SI]

Erick Lopez-Ornelas, Florence Sèdes. Cartographic Elements Extraction using High Resolution Remote Sensing Imagery and XML Modeling. IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2008), IEEE, Jul 2008, Boston, MA, United States. pp.125-136, ⟨10.1109/IGARSS.2008.4779020⟩. ⟨hal-03773755⟩