|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM217975674 |
| 003 |
DE-627 |
| 005 |
20250214005838.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231224s2012 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2012.2199127
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n0726.xml
|
| 035 |
|
|
|a (DE-627)NLM217975674
|
| 035 |
|
|
|a (NLM)22614643
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Yang, Wen
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a SAR-based terrain classification using weakly supervised hierarchical Markov aspect models
|
| 264 |
|
1 |
|c 2012
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Completed 26.12.2012
|
| 500 |
|
|
|a Date Revised 21.08.2012
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a 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
|
| 650 |
|
4 |
|a Journal Article
|
| 650 |
|
4 |
|a Research Support, Non-U.S. Gov't
|
| 700 |
1 |
|
|a Dai, Dengxin
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Triggs, Bill
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Xia, Gui-Song
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|d 1992
|g 21(2012), 9 vom: 07. Sept., Seite 4232-43
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:21
|g year:2012
|g number:9
|g day:07
|g month:09
|g pages:4232-43
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2012.2199127
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 21
|j 2012
|e 9
|b 07
|c 09
|h 4232-43
|