Title :
Residential area extraction by integrating supervised/unsupervised/contextual/object-based methods with moderate resolution remotely sensed data
Author :
Li, Congcong ; Wang, Lei ; Gong, Peng ; Wang, Jie ; Ying, Qing
Author_Institution :
State Key Lab. of Remote Sensing Sci., Beijing Normal Univ., Beijing, China
Abstract :
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.
Keywords :
cartography; land use planning; pattern classification; remote sensing; TM images; contextual classification method; contextual methods; global land cover mapping project; moderate resolution remotely sensed data; object based methods; residential area extraction; supervised methods; unsupervised methods; Image segmentation; Pixel; Remote sensing; Satellites; Shape; Support vector machines; Urban areas;
Conference_Titel :
Urban Remote Sensing Event (JURSE), 2011 Joint
Conference_Location :
Munich
Print_ISBN :
978-1-4244-8658-8
DOI :
10.1109/JURSE.2011.5764747
