Urban area detection from remotely sensed images using combination of local features

Detecting the urban area from very high resolution satellite images provides very useful results for urban planning and land use analysis. Since manual detection is very time consuming and prone to errors, automated systems to detect the urban area from very high resolution satellite images are needed. Unfortunately, diverse characteristics of the urban area and uncontrolled appearance of remote sensing images (illumination, viewing angle, etc.) increase the difficulty to develop automated systems. In order to overcome these difficulties, in this study we propose a novel urban area detection method using local features and a probabilistic framework. First, we introduce four different local feature extraction methods. Extracted local feature vectors serve as observations of the probability density function to be estimated. Using a variable kernel density estimation method, we estimate the corresponding probability density function. Using modes of the estimated density, as well as other probabilistic properties, we detect urban area boundaries in the image. We also introduce data and decision fusion methods to fuse information coming from different feature extraction methods. Extensive tests on very high resolution panchromatic Ikonos satellite images indicate the practical usefulness of the proposed method.