An Approach to Building Extraction in Natural Image

Author

Li Lingling ; Jin Taisong

Author_Institution

Dept. of Comput. Sci. & Applic., Zhengzhou Inst. of Aeronaut. Ind. Manage., Zhengzhou, China

fYear

2010

fDate

23-25 Sept. 2010

Firstpage

1

Lastpage

3

Abstract

A new approach to building extraction is proposed. Firstly, RPCL algorithm is used to improve segmentation granularity of super-pixel algorithm; Secondly, the spatial envelope pattern is used to classify image patches using support vector machine classifier, and distinguish building from non-building category in the image; Finally, building hypothesis in the image is verified based on parallel feature of the building in the image. The experiments on standard dataset show that the proposed algorithm outperforms other building extraction algorithms, and also meet the real-time requirements in general application.

Keywords

feature extraction; image classification; image segmentation; support vector machines; RPCL algorithm; building extraction; building hypothesis; image patches classification; natural image; segmentation granularity; spatial envelope pattern; super-pixel algorithm; support vector machine classifier; Buildings; Classification algorithms; Feature extraction; Image segmentation; Inference algorithms; Machine learning algorithms; Semantics;

fLanguage

English

Publisher

ieee

Conference_Titel

Wireless Communications Networking and Mobile Computing (WiCOM), 2010 6th International Conference on

Conference_Location

Chengdu

Print_ISBN

978-1-4244-3708-5

Electronic_ISBN

978-1-4244-3709-2

Type

conf

DOI

10.1109/WICOM.2010.5600648

Filename

5600648