Table 4 AR outcome of the FFODL-VDCAI approach with other models on the Stanford dataset.
From: Flying foxes optimization with reinforcement learning for vehicle detection in UAV imagery
Stanford dataset | |||
|---|---|---|---|
Methodology | \(AR^{max = 1}\) | \(AR^{max = 10}\) | \(AR^{max = 100}\) |
Faster R-CNN(Inceptionv2) | 15.10 | 17.10 | 17.10 |
Faster R-CNN(Resnet50) | 16.40 | 18.60 | 18.60 |
YOLO-v3 (320 × 320) | 9.00 | 9.10 | 9.10 |
YOLO-v4 (320 × 320) | 14.70 | 14.70 | 14.70 |
FFODL-VDCAI | 17.45 | 20.01 | 19.95 |
