PROJECT TITLE :

Spatiotemporal Detection and Analysis of Urban Villages in Mega City Regions of China Using High-Resolution Remotely Sensed Imagery

ABSTRACT:

Thanks to the speedy urbanization of China, several villages in the urban fringe are enveloped by ever-expanding cities and become therefore-known as urban villages (UVs) with substandard living conditions. Despite physical similarities to informal settlements in other countries (e.g., slums in India), UVs have access to basic public services, and more importantly, villagers own the land legitimately. The ensuing socio-economic impact on urban development attracts increasing interest. However, the identification of UVs in previous studies depends on fieldwork, resulting in late and incomplete analyses. In this paper, we tend to present 3 scene-based ways for detecting UVs using high-resolution remotely sensed imagery primarily based on a unique multi-index scene model and 2 standard scene models, i.e., bag-of-visual-words and supervised latent Dirichlet allocation. Within the experiments, our index-primarily based approach produced Kappa values around zero.82 and outperformed conventional models both quantitatively and visually. Moreover, we performed multitemporal classification to evaluate the transferability of training samples across multitemporal pictures with respect to three methods, and therefore the index-primarily based approach yielded best results once more. Finally, using the detection results, we conducted a systematic spatiotemporal analysis of UVs in Shenzhen and Wuhan, 2 mega cities of China. At the city level, we tend to observe the decline of UVs in urban areas over the recent years. At the block level, we have a tendency to characterize UVs quantitatively from physical and geometrical views and investigate the relationships between UVs and other geographic options. In each levels, the comparison between UVs in Shenzhen and Wuhan is made, and also the variations at intervals and across cities are revealed.