Research Article
Aircraft Detection for Remote Sensing Images Based on Deep Convolutional Neural Networks
Table 3
The comparison of multiple algorithms on AP for the aircraft.
| Method | Backbone | AP (%) | FPS |
| DConvNet [31] | ResNet-101 | 71.8 | 6.7 | DSSD [32] | ResNet-101 | 72.12 | 6.1 | FFSSD [33] | VGG-16 | 72.95 | 38.2 | ESSD [34] | VGG-16 | 73.08 | 37.3 | DC-SPP-YOLO [35] | Figure 5 in [35] | 73.16 | 33.5 | UAV-YOLO [36] | Figure 1 in [36] | 74.68 | 30.12 | RFN [37] | ResNet-101 | 79.1 | 6.5 | SigNMS [38] | VGG-16 | 80.6 | 6.7 | Improved-YOLOv3 [39] | Figure 4 in [39] | 86.42 | 25.8 | MRFF-YOLO [40] | Figure 5 in [40] | 87.16 | 25.1 | MSRDN-M(Ours) | Figure 11 | 90.66 | 25 |
|
|