A hierarchical scheme of multiple feature fusion for high-resolution satellite scene categorization

Authors:
Wen Shao;Wen Yang;Gui-Song Xia;Gang Liu
Affiliations:
School of Electronic Information, Wuhan University, Wuhan, China;School of Electronic Information, Wuhan University, Wuhan, China,Key State Laboratory LIESMARS, Wuhan University, Wuhan, China;Key State Laboratory LIESMARS, Wuhan University, Wuhan, China;School of Electronic Information, Wuhan University, Wuhan, China
Venue:
ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems
Year:
2013

Citing 5
Cited 0

Deriving texture feature set for content-based retrieval of satellite image database

ICIP '97 Proceedings of the 1997 International Conference on Image Processing (ICIP '97) 3-Volume Set-Volume 1 - Volume 1
Bag-of-visual-words and spatial extensions for land-use classification

Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems
Bag-of-colors for improved image search

MM '11 Proceedings of the 19th ACM international conference on Multimedia
Discriminative features for texture description

Pattern Recognition
Discriminative feature fusion for image classification

CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Scene categorization in high-resolution satellite images has attracted much attention in recent years. However, high intra-class variations, illuminations and occlusions make the task very challenging. In this paper, we propose a classification model based on a hierarchical fusion of multiple features. Highlights of our work are threefold: (1) we use four discriminative image features; (2) we employ support vector machine with histogram intersection kernel (HIK-SVM) and L1-regularization logistic regression classifier (L1R-LRC) in different classification stages, respectively. The soft probabilities of different features obtained by the HIK-SVM are discriminatively fused and fed into the L1R-LRC to obtain the final results; (3) we conduct an extensive evaluation of different configurations, including different feature fusion schemes and different kernel functions. Experimental analysis show that our method leads to state-of-the-art classification performance on the satellite scenes.