EOLib: An Image Information Mining Project

Kurzfassung

The abundance of available satellite images calls for their automated analysis and interpretation, including the semantic annotation of discovered objects as well as the monitoring of changes within image time series. A common approach is to cut large satellite image into contiguous patches and to classify each patch separately by attaching a semantic patch content label to it. In this context, the selected patch size is a critical parameter, as patches being too large may contain multiple objects and patches being too small may not be understandable due to missing contextual information. This approach has been embedded into an interactive active learning and exploitation environment within the ESA-funded EOLib project. The software of EOLib allows automated image data ingestion, feature extraction, and semantic image content annotation supported by interactive visualization tools. We report about our experiences with medium and high resolution Synthetic Aperture Radar (SAR) and optical multispectral image classification when using such an active learning approach. The most important phenomenon is the impact of image resolution. The higher the resolution, the higher the number of discernible land cover categories, in particular for built-up areas and industrial sites where we can see and interpret the impact of distinct human-made activities. Here, the discernible land cover categories depend on the actual image resolution. This becomes apparent when we compare the same target areas acquired by different space-borne SAR sensors (e.g., Sentinel-1A versus TerraSAR-X). In addition, it turns out that several country-specific regional surface cover categories can be trained and retrieved with SAR images that often appear differently in optical satellite images; however, any increase in classification accuracy has to be paid for by higher computational effort. Thus, EOLib represents an approach for future ground segments whose functionality will no longer be limited to the mere generation of level 1,2, or 3 products, but will include automated and user-friendly image content analysis and annotation.