We present some results on systems for automatically detecting bridges in high-resolution (2.5m) panchromatic IKONOS satellite images using texture information, geometric models, and combinations of both. A system using simple geometric models gives good results for bridges over roads and railroads, and very bad results for bridges over larger regions such as rivers. In contrast, a system using a texture-based classification and hand-made rules applied to that classification gives good results for bridges over rivers and railroads, and bad results for bridges over roads. We have explored several methods for combining both approaches to achieve an improved detection rate with only a moderate increase in the false alarm rate. Validation showed an increase in detection rate from 57% (geometry-based) and 33% (texture-based) to 71% (best combined system).