Research Article
UAV Image Small Object Detection Based on Composite Backbone Network
Table 2
mAPs of different networks on the Visdrone2019 datasets.
| Method | mAP | Car | Van | Bus | Truck | Motor | Tricycle | People | Pedestrian | Bicycle | Awning-tricycle | Ignored regions | Others |
| SSD300 | 11.47 | 0.43 | 0.21 | 0.26 | 0.21 | 0.08 | 0.05 | 0.04 | 0.07 | 0.00 | 0.02 | 0.00 | 0.01 | FSSD | 11.65 | 0.41 | 0.22 | 0.25 | 0.20 | 0.08 | 0.08 | 0.05 | 0.06 | 0.01 | 0.04 | 0.00 | 0.00 | YOLO3 | 14.21 | 0.46 | 0.26 | 0.30 | 0.26 | 0.11 | 0.09 | 0.06 | 0.09 | 0.02 | 0.04 | 0.00 | 0.02 | CBSSD | 19.00 | 0.61 | 0.26 | 0.35 | 0.26 | 0.21 | 0.13 | 0.15 | 0.21 | 0.04 | 0.05 | 0.00 | 0.00 |
|
|