Mapping and characterization of urban agriculture with QuickBird imagery in Lisbon

Remote sensing and spatial analysis of urban agriculture remains an under-researched topic, especially in cities of the 'developed world', despite the multiple valuable roles attributed to this activity. The work presented in this paper concerns the exploration of very high resolution (VHR) satellite imagery for detecting and characterizing urban agriculture in Lisbon. Different approaches of Geographic Object-Based Image Analysis were employed to extract agricultural use from a pan-sharpened QuickBird image, and results were compared. Agricultural areas were then characterized using a digital terrain model, and also a vegetation index computed from the multispectral bands. Results illustrate the potential and limitations of using VHR imagery and feature extraction methods to detect and monitor informal agriculture within a very heterogeneous urban fabric.