Table 3 Detection results of LR-DETR model on dataset for different categories.
From: River floating object detection with transformer model in real time
Class | Recall (%) | Precision (%) | mAP@0.5 (%) | mAP@0.5:0.95 (%) |
|---|---|---|---|---|
All | 73.7 | 71.9 | 76.0 | 47.7 |
Ball | 87.5 | 54.8 | 92.3 | 60.0 |
Bottle | 96.2 | 83.9 | 94.7 | 59.8 |
Branch | 58.1 | 76.6 | 66.7 | 37.4 |
Grass | 31.3 | 56.9 | 36.3 | 13.2 |
Leaf | 73.3 | 73.3 | 74.1 | 43.0 |
Milk-box | 88.9 | 78.4 | 86.5 | 57.6 |
Plastic-bag | 82.6 | 75.5 | 85.4 | 62.2 |
Plastic-garbage | 72.1 | 76.1 | 72.3 | 48.4 |
