Information Content of Very High Resolution SAR Images: Semantics, Geospatial Context, and Ontologies

The amount of collected Earth Observation (EO) data is increasing immensely with a rate of several Terabytes of data per day. Simultaneously with this increasing of data, new trends for exploration and information retrieval are highly needed. In the last year, the proposed method tries to explore the EO data using Image Information Mining (IIM) approach in which primitive feature extraction and classification are the main steps, developing a new process chain and a new taxonomy for the retrieved categories, mainly based on human interaction, can be a good solution. This paper proposes to explore the content of images and to identify the number of objects and land cover categories that can be retrieved from high resolution TerraSAR-X data. We need to mention that is for the first time when for remote sensing a large data set (e.g., TerraSAR-X images) covering different cities over the world is annotated and for each category a taxonomy for high resolution data is defined. Applications that may result from this study can be a semantic catalogue for TerraSAR-X, urban crisis, disasters, etc. First, we strongly need an automatic or semi-automatic searching tool capable to find in large EO data set similar sub-images (i.e. patches) and to group them in categories. Secondary, we need to define a taxonomy that can be used to semantically annotate each category using the human interaction. The data set consists of 109 scenes that cover different areas over the world: 5 scenes from Africa, 27 scenes from Asia, 44 scenes from Europe, 11 scenes from Middle East, and 22 scenes from North and South of America. These scenes are grouped in collections based on three criteria in order: (1) to get an idea about how many categories can be retrieved for each city/country/continent, (2) to see whether the same urban categories belong to two different scenes, and (3) to help us to annotate large data. Data set is grouped in more collections using previous three criteria and each collection is process separately using an enhanced methodology that take the scene/scenes and tile them into patches. Gabor filters is used as a primitive features method and is applied to each patch. Support vector machine with relevance feedback is implemented in order to group the features in categories of relevance. Finally, these categories are semantically annotated using as ground truth the Google Earth. In our investigation more than 850 categories were retrieved with their specific taxonomy. The novelty of this paper lies in the fact that this is the first time when a semantic annotation was made on a large number of scenes containing high resolution synthetic aperture radar images. This investigation has an important impact in applications such as classification of urban areas, infrastructure (e.g., airport, port, etc.), geography images (e.g., mountains, etc.), industrial sites, military sites, vegetation, and agriculture. The proposed taxonomies can be the basis for building a semantic catalogue for EO images. Finally, four types of query are defined and are planned to be integrated into the new system developed at DLR. The query provides opportunities to EO users to search into the database for some specific parameters or semantic of the existing data set