Table 3 Results of millimeter-wave radar and image fusion methods for object classification detection in the nuScenes test set
From: CenterTransFuser: radar point cloud and visual information fusion for 3D object detection
Methods | MDL | Car | Truck | Bus | Tralier | Const | Pedest | Motor | Bicycle | Traff | Barrier |
|---|---|---|---|---|---|---|---|---|---|---|---|
RSF [16] | R + C | 0.523 | 0.345 | 0.483 | – | – | 0.276 | 0.260 | 0.250 | – | – |
RRPN [17] | R + C | 0.418 | 0.447 | 0.572 | – | – | 0.171 | 0.305 | 0.214 | – | – |
CRFNet [13] | R + C | 0.491 | 0.267 | 0.431 | – | – | 0.347 | 0.210 | 0.140 | – | – |
CenterFusion [11] | R + C | 0.509 | 0.258 | 0.234 | 0.235 | 0.077 | 0.370 | 0.314 | 0.201 | 0.575 | 0.484 |
Our model | R + C | 0.535 | 0.278 | 0.328 | 0.243 | 0.065 | 0.422 | 0.387 | 0.217 | 0.601 | 0.476 |