Hierarchical Classification, Mining and Semantic Retrieval in Remote Sensing Image Archives

Summary:

Remotely sensed imagery has become an invaluable tool for scientists, governments and the general public to understand the world and its surrounding environment. Automatic content extraction and efficient access to this content have become highly desired goals for developing intelligent systems for effective processing of these images. This project aims to research automatic techniques for semantic classification and retrieval of remotely sensed images. Semantic processing will be done using pixel-based classification, region segmentation and classification, and scene analysis based on region spatial relationships. Content-based retrieval techniques will be studied to enable semantic searches by finding matches between conceptually similar scenes. Data mining methods will be studied to find interesting patterns in image databases and track their evolution in time.

People:

Duration:

October 2005 - October 2007

Sponsor:

FP6 Marie Curie Logo European Commission, FP6 Marie Curie International Reintegration Grant (Grant no: MIRG-CT-2005-017504)

Budget:

80,000 Euros

Publications: