Integrate vectorisation processing chain to IOTA².
Integrate vectorisation processing chain to IOTA² chain.
The processing chain dedicated to vectorise huge rasters is next to IOTA² scripts. As vectorisation scripts are fully operational, we can integrate them to the main chain. Users will be able to launch vectorisation thanks to the configuration file.
the steps summary should be as the following :
Group init:
[ ] Step 1: create directories
[ ] Step 2: generate common masks
[ ] Step 3: compute validity mask by tile
Group sampling:
[ ] Step 4: generate envelopes
[ ] Step 5: Prepare samples
[ ] Step 6: merge samples by models
[ ] Step 7: generate samples statistics
[ ] Step 8: select samples
[ ] Step 9: generate samples
[ ] Step 10: merge samples
[ ] Step 11: copy samples between models according to user request
Group learning:
[ ] Step 12: learning
Group classification:
[ ] Step 13: generate classification commands
[ ] Step 14: generate classifications
Group mosaic:
[ ] Step 15: classfication shaping
Group validation:
[ ] Step 16: confusion matrix command generation
[ ] Step 17: generate confusion matrix
[ ] Step 18: confusion matrix fusion
[ ] Step 19: report generation
Group vectorisation:
[ ] Step 20: foo
[ ] Step 21: bar
...
[ ] Step N: *