论文信息 - Residential area extraction by integrating supervised/unsupervised/contextual/object-based methods with moderate resolution remotely sensed data

Residential area extraction by integrating supervised/unsupervised/contextual/object-based methods with moderate resolution remotely sensed data

China is implementing a global land cover mapping project with 30 m resolution data around year 2000 and 2010. Mapping residential areas is an important component in this effort. In this paper, we present a new method for settlement area mapping. It integrates supervised method, unsupervised method, frequency based contextual classification method, and object based method. We test our method on three TM images. The results show that the method can improve the accuracy and the extraction result is easy to be manually checked and corrected.

[1] Qihao Weng,et al. A survey of image classification methods and techniques for improving classification performance , 2007 .

[2] D. Civco,et al. Mapping urban areas on a global scale: which of the eight maps now available is more accurate? , 2009 .

[3] Qiong Ran,et al. Settlement extraction in the North China Plain using Landsat and Beijing-1 multispectral data with an improved watershed segmentation algorithm , 2010 .

[4] M. Friedl,et al. Mapping global urban areas using MODIS 500-m data: new methods and datasets based on 'urban ecoregions'. , 2010 .

[5] Philip J. Howarth,et al. Land-use classification of SPOT HRV data using a cover-frequency method , 1992 .

[6] Limin Yang,et al. An approach for mapping large-area impervious surfaces: synergistic use of Landsat-7 ETM+ and high spatial resolution imagery , 2003 .

[7] R. Shibasaki,et al. GLOBAL URBAN AREA MAPPING IN HIGH RESOLUTION USING ASTER SATELLITE IMAGES , 2010 .