Table 1 Building extraction performance results (DGCNN)
From: Automatic LIDAR building segmentation based on DGCNN and euclidean clustering
Dataset | Accuracy | Precision | Recall | F-Score | IOU |
|---|---|---|---|---|---|
Dataset 1 | 89.00% | 0.90 | 0.86 | 0.87 | 0.78 |
Dataset 2 | 91.50% | 0.90 | 0.89 | 0.89 | 0.81 |
Dataset 3 | 85.20% | 0.79 | 0.81 | 0.80 | 0.68 |
Dataset 4 | 84.30% | 0.79 | 0.74 | 0.76 | 0.63 |
Dataset 5 | 83.4% | 0.83 | 0.77 | 0.79 | 0.67 |
Dataset 6 | 78.4% | 0.77 | 0.82 | 0.77 | 0.63 |
Dataset 7 | 85.8% | 0.82 | 0.83 | 0.83 | 0.71 |
Dataset 8 | 78.2% | 0.76 | 0.77 | 0.76 | 0.62 |