Statistics – Applications
Scientific paper
Sep 2004
adsabs.harvard.edu/cgi-bin/nph-data_query?bibcode=2004esasp.553e..23m&link_type=abstract
Proceedings of ESA-EUSC 2004 - Theory and Applications of Knowledge-Driven Image Information Mining with Focus on Earth Observa
Statistics
Applications
Scientific paper
In the framework of 3D visualization and real-time rendering of large remote sensing image databases, several signal processing techniques are presented and evaluated to filter/enhance SAR Digital Elevation Models (DEMs). Through the SRTM DEM, the interest of InSAR data for such applications is illustrated. A non stationary bayesian filter is presented to remove noise and small artefacts which pervade the SAR DEM while preserving structures and information content. Results obtained are very good, nevertheless large artefacts cannot be filtered and some artefacts remain. Therefore, image information have to be inserted to produce more realistic views. This second step is done by using a segmentation algorithm on the image data. By a topology analysis, the extracted objects are classified/stored in a tree structure to describe the topologic relations between the objects and reflect their interdependencies. An interactive learning procedure is done through a Graphical User Interface to link the signal classes to the semantic ones, i.e. to include human knowledge in the system. The selected information in form of objets are merged/fused in the DEM by assigning regularisation constraints.
Datcu Mihai
Maire Christian
No associations
LandOfFree
Synergy of Image and Digital Elevation Models (DEMS) Information for Virtual Reality does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Synergy of Image and Digital Elevation Models (DEMS) Information for Virtual Reality, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Synergy of Image and Digital Elevation Models (DEMS) Information for Virtual Reality will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-1064421