Mapping urban villages using fully convolutional neural networks

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.

[1]  Franklin Obeng-Odoom,et al.  Arrival City: How the Largest Migration in History Is Reshaping Our World , 2013 .

[2]  Him Chung.  Building an image of Villages-in-the-City: a clarification of China's distinct urban spaces. , 2010, International journal of urban and regional research.

[3]  T. Fent.  Department of Economic and Social Affairs, Population Division, United Nations Expert Group Meeting on Social and Economic Implications of Changing Population Age Structures , 2008 .

[4]  H. Taubenböck,et al.  The similar size of slums , 2018 .

[5]  Hannes Taubenböck,et al.  Large-scale building extraction in very high-resolution aerial imagery using Mask R-CNN , 2019, 2019 Joint Urban Remote Sensing Event (JURSE).

[6]  S. Ferrier,et al.  DEPARTMENT OF ECONOMIC AND SOCIAL AFFAIRS STATISTICS DIVISION UNITED NATIONS , 2008 .

[7]  Li Zhang,et al.  Self-help in housing and chengzhongcun in China's urbanization , 2003 .

[8]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[9]  Yanliu Lin,et al.  Understanding the ‘Village in the City’ in Guangzhou , 2011 .

[10]  Y. Zenou,et al.  Urban villages and housing values in China , 2012 .

[11]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Xiao Xiang Zhu,et al.  Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources , 2017, IEEE Geoscience and Remote Sensing Magazine.

[13]  Yanglin Wang,et al.  Urbanization and informal development in China: Urban villages in Shenzhen , 2009 .

[14]  Hui Liu,et al.  The Use of Landscape Metrics and Transfer Learning to Explore Urban Villages in China , 2017, Remote. Sens..

[15]  Sulochana Shekhar,et al.  DETECTING SLUMS FROM QUICK BIRD DATA IN PUNE USING AN OBJECT ORIENTED APPROACH , 2012 .

[16]  Xin Huang,et al.  Unsupervised Deep Feature Learning for Urban Village Detection from High-Resolution Remote Sensing Images , 2017 .

[17]  Xiao Xiang Zhu,et al.  Semantic segmentation of slums in satellite images using transfer learning on fully convolutional neural networks , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[18]  Hui Liu,et al.  Spatiotemporal Detection and Analysis of Urban Villages in Mega City Regions of China Using High-Resolution Remotely Sensed Imagery , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[19]  H. Taubenböck,et al.  Detecting social groups from space – Assessment of remote sensing-based mapped morphological slums using income data , 2018 .

[20]  H. Taubenböck,et al.  The morphology of the Arrival City - A global categorization based on literature surveys and remotely sensed data , 2018 .

[21]  Fulong Wu,et al.  Informality and the Development and Demolition of Urban Villages in the Chinese Peri-urban Area , 2013 .

[22]  Jiong Wang,et al.  Deprivation pockets through the lens of convolutional neural networks , 2019, Remote Sensing of Environment.

[23]  Fulong Wu,et al.  Urban villages under China's rapid urbanization: Unregulated assets and transitional neighbourhoods , 2010 .

[24]  Thomas Blaschke,et al.  Monitoring of “urban villages” in Shenzhen, China from high-resolution GF-1 and TerraSAR-X data , 2015, SPIE Remote Sensing.