Mapping urban villages using fully convolutional neural networks
Johannes Mast, Chuliang Wei, Michael Wurm
Abstract
Urban villages are a characteristic settlement type characterized by preserving their morphological characteristics embedded in sharp contrast in modern, high-rise developments found especially in fast growing urban agglomerations of China. They serve very important socioeconomic functions in terms of the provision of cheap housing for rural-urban migrants, but they are also considered controversial for local governments. Due to the unprecedented pace of urban growth, especially in the Pearl River Delta region (PRD), up-to-date information on the size and location of urban villages are mostly missing. Large-area but highly detailed data from earth observation platforms can provide crucial information for mapping urban villages based on their characteristic morphologies. This study deploys fully convolutional neural networks for mapping urban villages in the city of Shenzhen. Results of the underlying experiments show that very high mapping accuracies of 84% can be achieved.