OGRSS Data Fusion 2014
informations here
Contents
Submission
Proposed framework
We develop a complete framework to exploit jointly RGB and LWIR data. It consists in extracting relevant features from images, combine them and perform supervised classifications based on this set of features. Then, classification maps are combined using classifier fusion methodology.
The main steps of the proposed framework are:
Feature extraction
We exploit several features, from both data using:
- Dimensionality reduction using Principal Component Analysis (PCA) - Band selection - Statistics - OBIA ?
Reprojection
Supervised classification
- Pixel Based - Object Based
Fusion Of Classifier
Implementation
This methodology is based on algorithms all available in the ORFEO ToolBox library [3]. ORFEO Toolbox (OTB) is distributed as an open source library and offers particular functionalities for remote sensing image processing in general and for high spatial resolution images in particular. OTB is funded by the French Space Agency (CNES) and distributed under a free software license CeCILL (similar to GPL) to encourage contribution from users and to promote reproducible research.
Reproducibility
The product of this research will be a paper describing the methodology with the full computational environment used to produce the results.
References
[3] http://www.orfeo-toolbox.org/
Notes
Work schedule
Data Description
Training samples description
0 unclassified
- road
- trees
- red roof
- grey roof
- concrete roof
- vegetation
- bare soil
Tests
Training Samples description
TODO
Processing chain
different strategies (top down, bottom up):
- OBIA based : segment data and the classify each object(each segmented area) using high level features computed on each object
- pixel based : segment data at pixel level and then use post processing on classified map (segmentation, majority voting ...)
- Dimensionnality Reduction
PCA -> Matlab OTB (more than 99.99% info inone band) ICA , NAPCA ? TODO
- Reprojection
Using MVD1 -> Good results
- Extraction
- spectral distance
- Segmentation
- Meanshift
- TODO add spectral data
- watershed ...
- Classification
- SVM ?
- PostProcessing
- majority voting (on pixel based classification, useless if a segmentation step is present)
- Dempster Shaffer
First Processing chain
- SVM Classification on spectral data
TODO
Results
TODO
- First Processing chain -> OK
Add Background value to compute image statistics
Classification MAP regularization Add Post Processing using MeanShift (OBIA code Mickael) Test classification only on vegetation/tree class
- NOTES
Conf Mat SVM sur RGB
- 909 4 4 36 12 1 8
- 1 851 0 0 0 128 0
- 3 0 959 1 0 2 52
- 73 0 28 853 51 3 1
- 6 0 0 13 951 1 1
- 1 111 0 1 0 861 22
- 1 1 14 0 4 20 909
Conf Mat SVM sur RGB+PCA_LWIR
- 908 1 15 79 4 2 1
- 0 843 0 0 0 153 0
- 4 0 1037 3 1 0 6
- 27 0 11 937 38 0 0
- 2 0 1 11 903 1 0
- 0 80 1 1 0 887 19
- 0 1 1 0 2 18 993
Meilleurs résultats de la carte concaténée a part pour la séparation Vegetation/Arbre
Cross Validation classification comparison
TODO
Work Schedule
- Step 1 of the Classification Contest: NOW!
- Step 2 of the Classification Contest and opening of the Paper Contest: release of the full data set between February 16 and February 23, 2014. Announcement will be provided through this website and through the mailing list and the Linkedin group (see below) of the IADF Technical Committtee.
- Submission deadline for the Classification Contest: two weeks after Step 2