A multi-scale latent Dirichlet allocation model for object-oriented clustering of VHR panchromatic satellite images

TitleA multi-scale latent Dirichlet allocation model for object-oriented clustering of VHR panchromatic satellite images
Publication TypeJournal Article
Year of Publication2013
AuthorsTang, H., L. Shen, Y. Qi, Y. Cehn, Y. Shu, J. Li, and D. A. Clausi
JournalIEEE Transactions on Geoscience and Remote Sensing
Pagination1680 - 1692
Date Published03/2013
Keywordslatent Dirchlet allocation; scale space theory, object-oriented clustering, probabilistic topic models

A novel model is presented to address the problem of semantic clustering of geo-objects in VHR panchromatic satellite images. The proposed model combines a probabilistic topic model with a multi-scale image representation into an automatic framework by embedding both document and scale selections. The probabilistic topic model is used to characterize the statistical distributions of both intra-class appearance and inter-class coherence of geo-objects within documents, i.e., squared sub-images. Because the bag-of-words assumption involved in the probabilistic topic models does not consider the spatial coherence between topic labels, the multi-scale image representation is designed to provide a self-adaptive spatial regularization for various geo-object categories. By introducing scale and document selections, the automatic framework integrates the probabilistic topic model and the multi-scale image representation to ensure that words on a site should be allocated the same topic label no matter what documents they reside in. Consequently, unlike the traditional method of applying topic models for analyzing satellite images, the process of explicitly generating a set of documents before modeling and then combining multiple labels for a word on a given site is unnecessary. Gibbs sampling is adopted for parameter estimation and image clustering. Extensive experimental evaluations are designed to first analyze the effect of parameters in the proposed model and then compare the results of our model with those of some state-of-the-art methods for three different types of images. The results indicate that the proposed algorithm consistently outperforms these exiting state-of-the-art methods in all of the experiments.

Related files: