Paper Info
Title
Multi-feature probability topic scene classifier for high spatial resolution remote sensing imagery
Abstract
Scene classification can obtain the high-level semantic information in high spatial resolution (HSR) imagery. Probability topic model as a typical scene semantic representation has been successfully applied to nature scene by utilizing a single feature. However, it is not completely fit for HSR images due to the complexity of land cover classes. To solve the problem, multi-feature probability topic scene classifier based on Latent Dirichlet allocation (LDA), namely MFPTSC, is proposed for HSR imagery. In MFPTSC, the spectral, texture, and SIFT features as three representative features are firstly integrated. If the traditional multi-features fusion method (VIS-LDA) is used, which each feature vector is usually stacked at the visual word level, abundant information is lost, which leads to an undesirable classification performance. In this paper, a novel feature fusion strategy at the semantic allocation level, named SAL-LDA, is proposed to avoid information loss to a large extent by mining the latent semantics in accordance with the distinctive characteristics of each feature. Experiment results using the image dataset of 21 land-use classes demonstrate that the multi-feature fusion strategies of VIS-LDA and SAL-LDA both improve the classification accuracy, but the proposed SAL-LDA strategy is better than VIS-LDA.
Year
DOI
Venue
2014
10.1109/IGARSS.2014.6947071
IGARSS
Keywords
Field
DocType
visual word level,fusion,vis-lda,remote sensing,image representation,land cover,scene classification,sal-lda,feature vector,image fusion,semantic allocation level,high-level semantic information,multifeature probability topic scene classifier,image resolution,probability topic model,hsr images,spectral features,scene semantic representation,mfptsc,texture features,multi-feature,feature extraction,image classification,geophysical image processing,sift features,feature fusion strategy,hsr imagery,natural scenes,transforms,image texture,land cover class complexity,latent semantics mining,multifeatures fusion method,latent dirichlet allocation,high spatial resolution remote sensing imagery,nature scene,probability,information loss,resource management,satellites,accuracy,visualization,semantics
Scale-invariant feature transform,Latent Dirichlet allocation,Computer science,Remote sensing,Artificial intelligence,Classifier (linguistics),Computer vision,Feature vector,Pattern recognition,Topic model,Image resolution,Semantics,Visual Word
Conference
ISSN
Citations 
PageRank 
2153-6996
2
0.45
References 
Authors
9
3
Name
Order
Citations
PageRank
Qiqi Zhu1293.55
Yanfei Zhong2104490.58
Liangpei Zhang35448307.02