Generalized multiple kernel framework for multiclass geospatial objects detection in high-resolution remote sensing images

Li, Xiangjuan; Sun, Xian; Sun, Hao; Li, Yu; Wang, Hongqi

doi:doi:10.1117/1.OE.51.1.016203

GENERAL INFORMATION

You are not logged in Logged Out Log In

Optical Engineering / Volume 51 / Issue 1 / Remote Sensing

Previous Article | Next Article

Generalized multiple kernel framework for multiclass geospatial objects detection in high-resolution remote sensing images

Opt. Eng. 51, 016203 (Feb 11, 2012); http://dx.doi.org/10.1117/1.OE.51.1.016203

Alerts
- Alert Me When Cited
- Alert Me When Corrected
Tools
Share
- Email Abstract
- Connotea
- CiteULike
- del.icio.us
- BibSonomy
- Tweet this Article
- Add to Facebook

Abstract

References (25)

Citing Articles (8)

Xiangjuan Li, Hao Sun, and Yu Li

Chinese Academy of Sciences, Institute of Electronics, Key Laboratory of Technology in Geo-spatial Information Processing and Application System and Chinese Academy of Sciences, Graduate University, Beijing 100190, China

Xian Sun and Hongqi Wang

Chinese Academy of Sciences, Institute of Electronics, Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Beijing 100190, China

Multiclass geospatial objects detection within complex environments is a challenging problem in remote-sensing areas. In this paper we propose a novel, generalized kernel-based learning framework for the purpose of enhanced object detection. There are two novel areas. (1) Multisource information, including shape, feature points, and appearance, was extracted to give a comprehensive representation of the objects. We improved a shape descriptor and introduced a two-level spatial pyramid to represent appearance, both global and local. Therefore, basis kernels were formed, one for each feature. (2) In order to illustrate the effect of each kind of feature on each pyramid level, a generalized and weighted combination method was first used to combine all of the levels and then the features. The weights and the classifier model are based on the support vector machine framework for obtaining balance between all basis kernels. This classifier was transformed into a powerful detector by using a sliding window. The reported results are for the detection on high-resolution remote-sensing images. This study demonstrates that the proposed generalized and weighted combination of kernels can yield better performance compared with traditional single-kernel classifier and other combination methods.

History

Received Jul 29, 2011
Accepted Nov 14, 2011
Revised Oct 10, 2011
Published online Feb 11, 2012

Digital Object Identifier

http://dx.doi.org/10.1117/1.OE.51.1.016203

Citation

Xiangjuan Li, Xian Sun, Hao Sun, Yu Li and Hongqi Wang, "Generalized multiple kernel framework for multiclass geospatial objects detection in high-resolution remote sensing images", Opt. Eng. 51, 016203 (Feb 11, 2012); http://dx.doi.org/10.1117/1.OE.51.1.016203