Global View Segmentation Model Computer Vision Model
Dataset Version
Generated on Mar 18, 2026
Notes: Added 130 new images from Frankhauser 2026 global dataset. Added -10 and +10 degree rotation augmentation. Added -10% and +10% exposure augmentation.
1058 Total Images
View All Images
Dataset Split
Train Set 88%
926Images
Valid Set 8%
90Images
Test Set 4%
42Images
Preprocessing
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Rotation: Between -10° and +10°
Exposure: Between -10% and +10%