Monitoring and Analysis of Urban Sprawl Based on Road Network Data and High-Resolution Remote Sensing Imagery: A Case Study of China's Provincial Capitals

Abstract

The primary prerequisite for sustainable urban development is to accurately grasp the development of the city. The dynamic changes in the urban area can reflect the urban expansion process and spatial development model. Carrying out urban expansion monitoring and extracting urban areas is of great importance for grasping the law of urban development and promoting the sustainable development of cities. However, the related research reveals several problems such as insufficient accuracy and low intelligence of urban boundary extraction. In response to these problems, this paper proposes a new method for urban area extraction based on the progressive learning model. By combining prior knowledge and image features, the number of training samples required for machine learning is reduced, and the problem of using high-level semantic information expression in the process of urban areas is avoided by using the classification method, and thus the accuracy of urban area extraction is improved. The method uses urban road network data to divide the city into blocks. It applies the scene classification method to extract the urban areas and uses the pyramid layer-by-layer to carry out the space constraint method to integrate the urban extraction principle into the machine learning process, which can be obtained and kept artificial under a small sample condition. Extracting the effect of the urban area is very close, greatly reducing the workload and providing a new solution for high-precision automatic extraction of urban areas. Through the analysis of urban expansion, the following results were obtained: (1) from 2000 to 2015, China's provincial capital cities maintained a high-speed growth trend with a total area increased by 90%; (2) urban expansion showed significant regional differences. The eastern expansion rate gradually slowed down, the western and northeast regions accelerated their expansion, and the central region expanded steadily; (3) 61% of the provincial capital cities expanded exponentially; (4) the development of China's provincial capital cities was highly correlated with national urban development policies and regional development strategies.