The study on dynamic extraction of urban land use cover with remote sensing image based on AdaBoost algorithm

Rui Li; Jiulin Sun; Juanle Wang; Lijun Zhu; Rui Liu

doi:10.1117/12.833730

30 October 2009 The study on dynamic extraction of urban land use cover with remote sensing image based on AdaBoost algorithm

Rui Li, Jiulin Sun, Juanle Wang, Lijun Zhu, Rui Liu

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.

Citation Download Citation

Rui Li, Jiulin Sun, Juanle Wang, Lijun Zhu, and 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); https://doi.org/10.1117/12.833730

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available