Semantic Annotation of Satellite Images Using Latent Dirichlet Allocation

Liénou, Marie; Maître, H.; Datcu, Mihai

doi:10.1109/lgrs.2009.2023536

Cited by 250 publications

(137 citation statements)

References 10 publications

Supporting

Mentioning

137

Contrasting

Order By: Relevance

“…The most related work to ours is detailed in [16], where the authors only exploit different types of feature representation and do not make full use of the contextual information that may be beneficial to annotation tasks. Some other related studies [1,5,9] have investigated the application of topic model in satellite images annotation task. These studies did not apply multi-level features into classification framework [5] and introduced spatial information by means of cutting large image into small patches with an overlap and [9] employed Markov random field for the sake of utilizing the contextual information in satellite images.…”

Section: Discussionmentioning

confidence: 99%

“…Some other related studies [1,5,9] have investigated the application of topic model in satellite images annotation task. These studies did not apply multi-level features into classification framework [5] and introduced spatial information by means of cutting large image into small patches with an overlap and [9] employed Markov random field for the sake of utilizing the contextual information in satellite images. However we suggest that the CRF model is more suitable for discriminant tasks like image annotation or scene classification.…”

Section: Discussionmentioning

confidence: 99%

“…Some researchers have demonstrated that aspect models provide an understanding of aerial images in an effective way. According to [5,6], a scene of a satellite image, modeled by LDA, is represented as a finite mixture over some underlying semantic classes. This discriminative representation leads to a satisfactory result on annotation performance of large satellite images.…”

Section: Introductionmentioning

confidence: 99%

“…In order to solve this kind of problem, many methods and algorithms have been proposed. The authors in [5] have introduced spatial information by cutting the patches in the large image with an overlap. Various extensions of the aspect models have been also designed, e.g.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Tile-Level Annotation of Satellite Images Using Multi-Level Max-Margin Discriminative Random Field

Yang

Chen

2013

Remote Sensing

View full text Add to dashboard Cite

This paper proposes a multi-level max-margin discriminative analysis (M 3 DA) framework, which takes both coarse and fine semantics into consideration, for the annotation of high-resolution satellite images. In order to generate more discriminative topic-level features, the M 3 DA uses the maximum entropy discrimination latent Dirichlet Allocation (MedLDA) model. Moreover, for improving the spatial coherence of visual words neglected by M 3 DA, conditional random field (CRF) is employed to optimize the soft label field composed of multiple label posteriors. The framework of M 3 DA enables one to combine word-level features (generated by support vector machines) and topic-level features (generated by MedLDA) via the bag-of-words representation. The experimental results on high-resolution satellite images have demonstrated that, using the proposed method can not only obtain suitable semantic interpretation, but also improve the annotation performance by taking into account the multi-level semantics and the contextual information.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Tile-Level Annotation of Satellite Images Using Multi-Level Max-Margin Discriminative Random Field

Yang

Chen

2013

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Latent Dirichlet allocation (LDA) [4], an epoch-making Bayesian multi-topic analysis method, finds its application in various research fields including natural language processing, information retrieval and image analysis [2][5] [6][13] [14]. We can also apply an LDA-like Bayesian multi-topic analysis to microarray data, where we regard samples as documents and genes as words.…”

Section: Introductionmentioning

confidence: 99%

Bayesian Multi-topic Microarray Analysis with Hyperparameter Reestimation

Masada

Hamada

Shibata

et al. 2009

Advanced Data Mining and Applications

View full text Add to dashboard Cite

Abstract. This paper provides a new method for multi-topic Bayesian analysis for microarray data. Our method achieves a further maximization of lower bounds in a marginalized variational Bayesian inference (MVB) for Latent Process Decomposition (LPD), which is an effective probabilistic model for microarray data. In our method, hyperparameters in LPD are updated by empirical Bayes point estimation. The experiments based on microarray data of realistically large size show efficiency of our hyperparameter reestimation technique. . We can also apply an LDA-like Bayesian multi-topic analysis to microarray data, where we regard samples as documents and genes as words. However, microarray data are given as a real matrix, not as a non-negative integer matrix. Therefore, researchers apply LDA after introducing Gaussian distributions in place of word multinomial distributions and provide an efficient probabilistic model, Latent Process Decomposition (LPD) [9], where topics in LDA are called processes. As we can find Dirichlet prior distributions for word multinomials in LDA, we can find prior distributions for Gaussian distributions in LPD. To be precise, Gaussian priors are prepared for mean parameters, and Gamma priors are for precision parameters. However, as far as we know, there are still no reports on how we can reestimate hyperparameters, i.e., parameters of these prior distributions, and there are also no reports on whether we can improve microarray analysis by using hyperparameter reestimation. Therefore, in this paper, we provide a hyperparameter reestimation technique for LPD and show the results of experiments using microarray data of realistically large size. IntroductionOur method is based on a marginalized variational Bayesian inference (MVB) proposed by Ying et al. [15]. Marginalized variational Bayesian inference, alternatively called collapsed variational Bayesian inference [12], theoretically achieves better lower bounds than conventional variational Bayesian inferences

show abstract

Semantic Analysis of Satellite Image Time Series

Dumitru

Datcu

2021

Change Detection and Image Time Series Analysis 2

Self Cite

View full text Add to dashboard Cite

Large archives of satellite images have been created over time. The existence of these archives enables us to extract evolutions of the same of same geographic area over time, creating satellite image time series (SITS). As SITS represent an amount of information far greater than individual images, their analysis is complex and difficult. In this paper we propose a new unsupervised SITS analysis method based on the latent Dirichlet allocation (LDA) model, a hierarchical model originally developed for text analysis. In this model documents are represented as random mixture of latent topics, each topic being characterized by a distribution over words. This paper extends the use of LDA model for satellite image time series analysis by proposing a description language for SITS modeling according to the LDA model, and is applied on a SITS of 11 Landsat TM scenes acquired in 2007.

show abstract

Semantic Annotation of Satellite Images Using Latent Dirichlet Allocation

Cited by 250 publications

References 10 publications

Tile-Level Annotation of Satellite Images Using Multi-Level Max-Margin Discriminative Random Field

Tile-Level Annotation of Satellite Images Using Multi-Level Max-Margin Discriminative Random Field

Bayesian Multi-topic Microarray Analysis with Hyperparameter Reestimation

Semantic Analysis of Satellite Image Time Series

Contact Info

Product

Resources

About