Extraction of urban impervious surface information based on object-oriented technology

Aixia Liu; Xiaojie Zhao; Jing Wang; Ting He

doi:10.1117/12.2029055

24 October 2013 Extraction of urban impervious surface information based on object-oriented technology

Aixia Liu, Xiaojie Zhao, Jing Wang, Ting He

Proceedings Volume 8893, Earth Resources and Environmental Remote Sensing/GIS Applications IV; 88931K (2013) https://doi.org/10.1117/12.2029055
Event: SPIE Remote Sensing, 2013, Dresden, Germany

Abstract

Impervious surface is an important part of urban underlying surface, as well as an important monitoring index for city ecological system and environment changes. However, accurate impervious surface extraction is still a challenge. This paper uses the color, shape and overall heterogeneity features from the high spatial resolution remote sensing image to extract the impervious surface. An edge-based image segmentation algorithm is put forward to fuse heterogeneous objects which integrates edge features and multi-scale segmentation algorithm and uses the edge information to guide image objects generation. Results showed that this method can greatly improve the accuracy of image segmentation. Accuracy assessment indicated that the overall impervious surface classification accuracy and a Kappa coefficient yield 87% and 0.84, respectively.

Citation Download Citation

Aixia Liu, Xiaojie Zhao, Jing Wang, and Ting He "Extraction of urban impervious surface information based on object-oriented technology", Proc. SPIE 8893, Earth Resources and Environmental Remote Sensing/GIS Applications IV, 88931K (24 October 2013); https://doi.org/10.1117/12.2029055

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