• xmlui.mirage2.page-structure.header.title
    • français
    • English
  • Help
  • Login
  • Language 
    • Français
    • English
View Item 
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Browse

BIRDResearch centres & CollectionsBy Issue DateAuthorsTitlesTypeThis CollectionBy Issue DateAuthorsTitlesType

My Account

LoginRegister

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors
Thumbnail - Request a copy

SAR-based Terrain Classification using Weakly Supervised Hierarchical Markov Aspect Models

Xia, Gui-Song; Triggs, Bill; Dai, Dengxin; Yang, Wen (2012), SAR-based Terrain Classification using Weakly Supervised Hierarchical Markov Aspect Models, IEEE Transactions on Image Processing, 21, 9, p. 4232-4243. http://dx.doi.org/10.1109/TIP.2012.2199127

Type
Article accepté pour publication ou publié
Date
2012
Journal name
IEEE Transactions on Image Processing
Volume
21
Number
9
Publisher
IEEE
Pages
4232-4243
Publication identifier
http://dx.doi.org/10.1109/TIP.2012.2199127
Metadata
Show full item record
Author(s)
Xia, Gui-Song
Triggs, Bill cc
Dai, Dengxin
Yang, Wen
Abstract (EN)
We introduce the hierarchical Markov aspect model (HMAM), a computationally efficient graphical model for densely labeling large remote sensing images with their underlying terrain classes. HMAM resolves local ambiguities efficiently by combining the benefits of quadtree representations and aspect models--the former incorporate multiscale visual features and hierarchical smoothing to provide improved local label consistency, while the latter sharpen the labelings by focusing them on the classes that are most relevant for the broader local image context. The full HMAM model takes a grid of local hierarchical Markov quadtrees over image patches and augments it by incorporating a probabilistic latent semantic analysis aspect model over a larger local image tile at each level of the quadtree forest. Bag-of-word visual features are extracted for each level and patch, and given these, the parent-child transition probabilities from the quadtree and the label probabilities from the tile-level aspect models, an efficient forwards-backwards inference pass allows local posteriors for the class labels to be obtained for each patch. Variational expectation-maximization is then used to train the complete model from either pixel-level or tile-keyword-level labelings. Experiments on a complete TerraSAR-X synthetic aperture radar terrain map with pixel-level ground truth show that HMAM is both accurate and efficient, providing significantly better results than comparable single-scale aspect models with only a modest increase in training and test complexity. Keyword-level training greatly reduces the cost of providing training data with little loss of accuracy relative to pixel-level training.
Subjects / Keywords
synthetic aperture radar; scene labeling; probabilistic latent semantic analysis (PLSA); Hierarchical Markov aspect model (HMAM)

Related items

Showing items related by title and author.

  • Thumbnail
    Cascade filtering of high-resolution SAR images with L0 smoothing 
    Liu, Gang; Yang, Wen; Xia, Gui-Song; Shao, Wen (2012) Communication / Conférence
  • Thumbnail
    Statistical Mid-Level Features for Building-up Area Extraction From Full Polarimetric SAR Imagery 
    Yang, Wen; Liu, Y.; Xia, Gui-Song; Xu, X. (2012) Article accepté pour publication ou publié
  • Thumbnail
    Optimal Transport Mixing of Gaussian Texture Models 
    Aujol, Jean-François; Peyré, Gabriel; Xia, Gui-Song; Ferradans, Sira (2012) Document de travail / Working paper
  • Thumbnail
    Synthesizing and Mixing Stationary Gaussian Texture Models 
    Aujol, Jean-François; Peyré, Gabriel; Ferradans, Sira; Xia, Gui-Song (2014) Article accepté pour publication ou publié
  • Thumbnail
    Mid-level features and spatio-temporal context for activity recognition 
    Yuan, Fei; Xia, Gui-Song; Sahbi, Hichem; Prinet, Véronique (2012) Article accepté pour publication ou publié
Dauphine PSL Bibliothèque logo
Place du Maréchal de Lattre de Tassigny 75775 Paris Cedex 16
Phone: 01 44 05 40 94
Contact
Dauphine PSL logoEQUIS logoCreative Commons logo