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

This paper proposes a multi-level max-margin discriminative analysis (M3DA) 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 M3DA uses the maximum entropy discrimination latent Dirichlet Allocation (MedLDA) model. Moreover, for improving the spatial coherence of visual words neglected by M3DA, conditional random field (CRF) is employed to optimize the soft label field composed of multiple label posteriors. The framework of M3DA 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.

[1]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[2]  Thomas Hofmann,et al.  Unsupervised Learning by Probabilistic Latent Semantic Analysis , 2004, Machine Learning.

[3]  Frédéric Jurie,et al.  Latent mixture vocabularies for object categorization and segmentation , 2009, Image Vis. Comput..

[4]  Bill Triggs,et al.  Region Classification with Markov Field Aspect Models , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Fei-Fei Li,et al.  Image Segmentation with Topic Random Field , 2010, ECCV.

[6]  David M. Blei,et al.  Supervised Topic Models , 2007, NIPS.

[7]  Vladimir Kolmogorov,et al.  What energy functions can be minimized via graph cuts? , 2002, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Gui-Song Xia,et al.  SAR-Based Terrain Classification Using Weakly Supervised Hierarchical Markov Aspect Models , 2012, IEEE Transactions on Image Processing.

[9]  Yunhao Chen,et al.  An Object-Oriented Semantic Clustering Algorithm for High-Resolution Remote Sensing Images Using the Aspect Model , 2011, IEEE Geoscience and Remote Sensing Letters.

[10]  Anton Osokin,et al.  Fast Approximate Energy Minimization with Label Costs , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Eric P. Xing,et al.  MedLDA: maximum margin supervised topic models for regression and classification , 2009, ICML '09.

[12]  Mihai Datcu,et al.  Semantic Annotation of Satellite Images Using Latent Dirichlet Allocation , 2010, IEEE Geoscience and Remote Sensing Letters.

[13]  W. Eric L. Grimson,et al.  Spatial Latent Dirichlet Allocation , 2007, NIPS.

[14]  Yang Wang,et al.  Max-margin Latent Dirichlet Allocation for Image Classification and Annotation , 2011, BMVC.

[15]  Hong Sun,et al.  Unsupervised Satellite Image Classification Using Markov Field Topic Model , 2013, IEEE Geoscience and Remote Sensing Letters.

[16]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..