Paper
24 October 2013 Object-based change detection in rapid urbanization regions with remotely sensed observations: a case study of Shenzhen, China
Lihuang He, Guihua Dong, Wei-Min Wang, Lijun Yang, Hong Liang
Author Affiliations +
Abstract
China, the most populous country on Earth, has experienced rapid urbanization which is one of the main causes of many environmental and ecological problems. Therefore, the monitoring of rapid urbanization regions and the environment is of critical importance for their sustainable development. In this study, the object-based classification is employed to detect the change of land cover in Shenzhen, which is located in South China and has been urbanized rapidly in recent three decades. First, four Landsat TM images, which were acquired on 1990, 2000 and 2010, respectively, are selected from the image database. Atmospheric corrections are conducted on these images with improved dark-object subtraction technique and surface meteorological observations. Geometric correction is processed with ground control points derived from topographic maps. Second, a region growing multi-resolution segmentation and a soft nearest neighbour classifier are used to finish object-based classification.

After analyzing the fraction of difference classes over time series, we conclude that the comparison of derived land cover classes with socio-economic statistics demonstrates the strong positive correlation between built-up classes and urban population as well as gross GDP and GDPs in second and tertiary industries. Two different mechanisms of urbanization, namely new land development and redevelopment, are revealed. Consequently, we found that, the districts of Shenzhen were urbanized through different mechanisms.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Lihuang He, Guihua Dong, Wei-Min Wang, Lijun Yang, and Hong Liang "Object-based change detection in rapid urbanization regions with remotely sensed observations: a case study of Shenzhen, China", Proc. SPIE 8893, Earth Resources and Environmental Remote Sensing/GIS Applications IV, 88931W (24 October 2013); https://doi.org/10.1117/12.2031675
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Earth observing sensors

Landsat

Image classification

Image processing

Environmental sensing

Process control

Back to Top