- LBP Features: For the local binary patterns, we used the ‘uniform’ method which is grayscale invariant and rotation invariant. We used a radius of 1 (i.e. we calculated the LBP for each pixel using only the 8-neighbourhood).
- LBP Histograms: We flatten the LBP features and calculate the histogram on it using 10 bins.
The LBP histograms were used as the feature used to train the model.
Precision (UA) | Recall (PA) | F1-Score | Accuracy | OE | CE | |
---|---|---|---|---|---|---|
Flooded | 0.70 | 0.86 | 0.77 | - | 0.14 | 0.30 |
Non-Flooded | 0.81 | 0.64 | 0.72 | - | 0.36 | 0.19 |
Macro Avg | 0.76 | 0.75 | 0.74 | 0.75 | 0.25 | 0.24 |
It used the LBP features from the training set as training data.
- Poly kernel, C=3
Precision (UA) | Recall (PA) | F1-Score | Accuracy | OE | CE | |
---|---|---|---|---|---|---|
Flooded | 0.53 | 0.81 | 0.64 | - | 0.19 | 0.47 |
Non-Flooded | 0.59 | 0.28 | 0.38 | - | 0.72 | 0.41 |
Macro Avg | 0.56 | 0.54 | 0.51 | 0.54 | 0.46 | 0.44 |
- RBF kernel, C=3
Precision (UA) | Recall (PA) | F1-Score | Accuracy | OE | CE | |
---|---|---|---|---|---|---|
Flooded | 0.80 | 0.59 | 0.68 | - | 0.41 | 0.20 |
Non-Flooded | 0.68 | 0.86 | 0.76 | - | 0.14 | 0.32 |
Macro Avg | 0.74 | 0.72 | 0.72 | 0.72 | 0.28 | 0.26 |
- RBF, C=3, gamma=0.05
Precision (UA) | Recall (PA) | F1-Score | Accuracy | OE | CE | |
---|---|---|---|---|---|---|
Flooded | 0.74 | 0.84 | 0.79 | - | 0.16 | 0.26 |
Non-Flooded | 0.82 | 0.71 | 0.76 | - | 0.29 | 0.18 |
Macro Avg | 0.78 | 0.78 | 0.77 | 0.775 | 0.22 | 0.22 |
Precision (UA) | Recall (PA) | F1-Score | Accuracy | OE | CE | |
---|---|---|---|---|---|---|
Flooded | 1.00 | 0.97 | 0.99 | - | 0.03 | 0.00 |
Non-Flooded | 0.97 | 1.00 | 0.99 | - | 0.00 | 0.03 |
Macro Avg | 0.99 | 0.99 | 0.99 | 0.985 | 0.01 | 0.01 |
Precision (UA) | Recall (PA) | F1-Score | Accuracy | OE | CE | |
---|---|---|---|---|---|---|
Flooded | 0.97 | 0.99 | 0.98 | - | 0.01 | 0.03 |
Non-Flooded | 0.99 | 0.97 | 0.98 | - | 0.03 | 0.01 |
Macro Avg | 0.98 | 0.98 | 0.98 | 0.978 | 0.02 | 0.02 |
Precision (UA) | Recall (PA) | F1-Score | Accuracy | OE | CE | |
---|---|---|---|---|---|---|
Flooded | 0.97 | 1.00 | 0.99 | - | 0.00 | 0.03 |
Non-Flooded | 1.00 | 0.97 | 0.99 | - | 0.03 | 0.00 |
Macro Avg | 0.99 | 0.99 | 0.99 | 0.985 | 0.01 | 0.01 |
- U-Net.
- ISODATA.
- K-Means.
Abdelrahman Jamal |
Iten Elhak |
Radwa Ahmed |
Abdullah Alshawafi |