Download - Semantic search applied to Earth Observation products

Transcript
Page 1: Semantic search applied to Earth Observation products

Semantic search applied to Earth Observation products

Jerome Gasperi @ CNES | 82th OGC Technical Commitee | Seoul, Korea - October 10th, 2012

Page 2: Semantic search applied to Earth Observation products
Page 3: Semantic search applied to Earth Observation products

?How to search for Earth Observation imagerythat contains coastal cultivated areas ?

Page 4: Semantic search applied to Earth Observation products

Orthorectified image Characterized image

This is urban

This is water

This is forest

What we got What we need

Page 5: Semantic search applied to Earth Observation products

How to do this ?

Page 6: Semantic search applied to Earth Observation products

Semantic content extraction from image is a complex and time consuming task

Page 7: Semantic search applied to Earth Observation products

A different and simpler approach is to use the metadata footprint against exogenous

data to perform image characterization

Page 8: Semantic search applied to Earth Observation products

SLACkERSimpLe Automated Characterization of EaRth observation products

Page 9: Semantic search applied to Earth Observation products

SLACkER uses Global Land Cover 2000 classification to perform automatic

characterization of Earth Observation products

Page 10: Semantic search applied to Earth Observation products

World land coverTIFF file ~ 650 Mo1 km resolution1 color = 1 thematic class22 classes

Global Land Cover 2000

Page 11: Semantic search applied to Earth Observation products

Metadata

IdentifierDescriptionCopyrightAcquisition dateAcquisition anglesThumbnail...+ Footprint

SLACkER

1. Get footprint bounding box 2. Get corresponding GLC2000 area

3. Process characterization 4. Store results within database

Inge

stio

nSearch

Page 12: Semantic search applied to Earth Observation products

Tag table images within database glc2000 >> Add classification columns >> Processing 10 Crop GLC2000 raster : 24137 6169 156 119 Polygonize extracted raster Process footprint against Global Land Cover Store classification => 40.89% of Deserts (10 + 14 + 19) => 31.89% of Herbaceous (9 + 11 + 12 + 13) => 14.71% of Water (20) => 9.27% of Cultivated (15 + 16 + 17 + 18) => 3.2% of Forests (1 + 2 + 3 + 4 + 5 + 6)

( 28.65 % of 14 : Sparse Herbaceous or sparse Shrub Cover ) ( 6.1 % of 18 : Mosaic: Cropland / Shrub or Grass Cover ) ( 12.24 % of 19 : Bare Areas ) ( 31.88 % of 12 : Shrub Cover, closed-open, deciduous ) ( 2.5 % of 3 : Tree Cover, broadleaved, deciduous, open ) ( 14.71 % of 20 : Water Bodies (natural & artificial) ) ( 0.13 % of 15 : Regularly flooded Shrub and/or Herbaceous Cover ) ( 2.81 % of 16 : Cultivated and managed areas ) ( 0.69 % of 4 : Tree Cover, needle-leaved, evergreen ) ( 0.21 % of 17 : Mosaic: Cropland / Tree Cover / Other natural vegetation )

Processing result example

Page 13: Semantic search applied to Earth Observation products

https://vimeo.com/51045597

Page 14: Semantic search applied to Earth Observation products

What's next

Page 15: Semantic search applied to Earth Observation products

md

SLACkER classification

Provide classification service through WPS

Page 16: Semantic search applied to Earth Observation products

Segmentation+classification processing with OTB*

Additionnaly, provide a "true" WPS classification service based on the OTB suite service

*OTB is the Orfeo ToolBox - http://www.orfeo-toolbox.org/otb/

Page 17: Semantic search applied to Earth Observation products