Table 17 Detailed classification test results for the Houston Dataset in terms of Precision, Recall, and F1-Score. Testing was done with PCA 30 CEU-Net no-patching with a 75%/25% Training/Testing split
From: CEU-Net: ensemble semantic segmentation of hyperspectral images using clustering
Class Labels | Precision | Recall | f1-score | Support |
|---|---|---|---|---|
Healthy Grass | 0.99 | 0.99 | 0.99 | 355 |
Stressed Grass | 0.98 | 1.00 | 0.99 | 354 |
Artificial Turf | 1.00 | 1.00 | 1.00 | 185 |
Trees | 0.99 | 1.00 | 0.99 | 308 |
Soil | 1.00 | 0.99 | 1.00 | 322 |
Water | 1.00 | 1.00 | 1.00 | 69 |
Residential | 0.99 | 0.97 | 0.98 | 316 |
Commercial | 1.00 | 0.99 | 0.99 | 78 |
Roads | 0.99 | 0.97 | 0.98 | 369 |
Highway | 0.97 | 0.99 | 0.98 | 361 |
Railways | 0.99 | 0.98 | 0.98 | 424 |
Parking Lot 1 | 0.95 | 0.98 | 0.97 | 354 |
Parking Lot 2 | 0.93 | 0.85 | 0.89 | 67 |
Tennis Court | 1.00 | 0.99 | 1.00 | 126 |
Running Track | 1.00 | 1.00 | 1.00 | 159 |
Accuracy | Â | Â | 0.98 | 3847 |
Macro Average | 0.99 | 0.98 | 0.98 | 3847 |
Weighted Average | 0.98 | 0.98 | 0.98 | 3847 |