THESIS

RIGID PAVEMENT

Instance Segmentation

RIGID PAVEMENT Image Dataset

v2

RIGID PAVEMENT

Generated on Feb 6, 2024

Dataset Split

Train Set 92%
1914Images
Valid Set 5%
112Images
Test Set 2%
50Images

Preprocessing

Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 25-75% Vertical Region
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Shear: ±15° Horizontal, ±15° Vertical
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 1.01% of pixels