30 October 2009 The study on dynamic extraction of urban land use cover with remote sensing image based on AdaBoost algorithm
Author Affiliations +
Proceedings Volume 7498, MIPPR 2009: Remote Sensing and GIS Data Processing and Other Applications; 74981U (2009) https://doi.org/10.1117/12.833730
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China
Abstract
In China, the contradiction of urban land use and cultivated land use is predominant, it's important to detect the urban land use cover for the guide of urban development. The primary problem of dynamic detecting on urban land use cover is how to get accurate classification of remote sensing data. Theoretically, if combining several low precision classifiers, a better classification result can be made and this paper introduces how to combine the low precision urban land use cover classifiers. We use CBERS (China-Brazil Earth Resources Satellite) remote sensing images of the year 2007 for Shanghai's urban land use cover. We adopt the AdaBoost combination classifier, which combines spectral feature information, texture structure information and improved Normalized Difference Built-up Index (NDBI) to improve the individual classification precision. The experiment results show that a notable improvement of classification precision of urban land use cover is achieved after using AdaBoost algorithm.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Rui Li, Jiulin Sun, Juanle Wang, Lijun Zhu, Rui Liu, "The study on dynamic extraction of urban land use cover with remote sensing image based on AdaBoost algorithm", Proc. SPIE 7498, MIPPR 2009: Remote Sensing and GIS Data Processing and Other Applications, 74981U (30 October 2009); doi: 10.1117/12.833730; https://doi.org/10.1117/12.833730
PROCEEDINGS
8 PAGES


SHARE
Back to Top