Scene classification based on spatial pyramid representation by superpixel lattices and contextual visual features

Gu, Guanghua; Li, Fengcai; Zhao, Yao; Zhu, Zhenfeng

doi:doi:10.1117/1.OE.51.1.017201

My Subscription | My Email Alerts | My Article Collections

GENERAL INFORMATION

You are not logged in Logged Out Log In

Optical Engineering / Volume 51 / Issue 1 / Machine Vision, Pattern Recognition

Previous Article | Next Article

Scene classification based on spatial pyramid representation by superpixel lattices and contextual visual features

Opt. Eng. 51, 017201 (Feb 07, 2012); http://dx.doi.org/10.1117/1.OE.51.1.017201

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 (36)

Citing Articles (24)

Guanghua Gu, Yao Zhao, and Zhenfeng Zhu

Beijing Jiaotong University, Institute of Information Science

Fengcai Li

YanShan University, School of Information Science and Engineering, Qinhuangdao, China

Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China

Natural scene classification is a challenging open problem in computer vision. We present a novel spatial pyramid representation scheme for recognizing scene category. Initially, each image is partitioned into sub-blocks, applying the technology of superpixel lattices segmentation according to a boosted edge learning boundary map, which makes the objects in each sub-block have the integrity—that is, the features in each sub-block are relatively consistent. Then, we extract the dense scale-invariant feature transform features of the images and form the contextual visual feature description. Finally, the image representations are performed by following the methodology of spatial pyramid. The feature descriptions we present include both local structural information and global spatial structural information; therefore, they are more discriminative for scene classification. Experiments demonstrate that the classification rate can achieve about 87.13% on a set of 15 categories of complex scenes.

History

Received May 27, 2011
Accepted Nov 03, 2011
Revised Oct 31, 2011
Published online Feb 07, 2012

Digital Object Identifier

http://dx.doi.org/10.1117/1.OE.51.1.017201

Citation

Guanghua Gu, Fengcai Li, Yao Zhao and Zhenfeng Zhu, "Scene classification based on spatial pyramid representation by superpixel lattices and contextual visual features", Opt. Eng. 51, 017201 (Feb 07, 2012); http://dx.doi.org/10.1117/1.OE.51.1.017201