Skip to content

Improve vegetation regularization #44

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ytanguy wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Improve vegetation regularization #44

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
24e388e
Fix regularization of vegetation : invert two steps and replace 0 by …
ytanguy Feb 25, 2026
a151d69
Fix regularization of vegetation : invert two steps and replace 0 by …
ytanguy Feb 25, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
39 changes: 23 additions & 16 deletions slurp/masks/vegetationmask.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -597,6 +597,29 @@ def clean_task(
valid_stack = input_buffers[1][0]
im_ndvi = input_buffers[2][0]

# Filter final mask with a NDVI threshold (1st cluster of vegetation)
# -> allows to have better shapes : pixels around a low veg area will be
# classified as bare ground
im_classif = np.where(
im_classif == LOW_VEG_CLASS,
np.where(
im_ndvi > params["min_ndvi_veg"],
LOW_VEG_CLASS,
UNDEFINED_VEG + LOW_VEG_CLASS,
),
im_classif,
)
# pixels around trees will be classified as middle texture
im_classif = np.where(
im_classif > LOW_VEG_CLASS,
np.where(
im_ndvi > params["min_ndvi_veg"],
VEG_CODE + MIDDLE_TEXTURE_CODE,
UNDEFINED_VEG + MIDDLE_TEXTURE_CODE,
),
im_classif,
)

if params["remove_small_objects"]:
high_veg_binary = np.where(im_classif > LOW_VEG_CLASS, True, False)
high_veg_binary = apply_morpho(
Expand Down Expand Up @@ -628,22 +651,6 @@ def clean_task(
np.logical_and(im_classif > LOW_VEG_CLASS, low_veg_binary == 1)
] = LOW_VEG_CLASS

# Filter final mask with a NDVI threshold (1st cluster of vegetation)
# TODO : replace 0 by UNDEFINED_VEG ?
im_classif = np.where(
im_classif == LOW_VEG_CLASS,
np.where(im_ndvi > params["min_ndvi_veg"], LOW_VEG_CLASS, 0),
im_classif,
)
# TODO : replace 0 by UNDEFINED_VEG + MIDDLE_TEXTURE_CODE
im_classif = np.where(
im_classif > LOW_VEG_CLASS,
np.where(
im_ndvi > params["min_ndvi_veg"], VEG_CODE + MIDDLE_TEXTURE_CODE, 0
),
im_classif,
)

im_classif = np.where(valid_stack == 0, im_classif, NODATA_INT8)

return im_classif
Expand Down
Loading