Research Article
Pillar-Based 3D Object Detection from Point Cloud with Multiattention Mechanism
Table 8
Results on the KITTI test average orientation similarity (AOS) detection benchmark.
| | Model | Car | Pedestrian | Cyclist | | Easy (%) | Mod. (%) | Hard (%) | mAP (%) | Easy (%) | Mod. (%) | Hard (%) | mAP (%) | Easy (%) | Mod. (%) | Hard (%) | mAP (%) |
| | PointPillars | 90.19 | 88.76 | 86.38 | 88.44 | 32.39 | 31.41 | 29.84 | 31.21 | 82.43 | 68.16 | 61.96 | 70.85 | | PointPillars + channel attention | 90.55 | 88.75 | 87.09 | 88.79 | 54.61 | 50.27 | 47.38 | 50.75 | 84.24 | 70.09 | 65.78 | 73.37 | | PointPillars + SOCA | 90.61 | 88.91 | 87.24 | 88.92 | 58.30 | 53.48 | 50.37 | 54.05 | 83.99 | 71.85 | 68.41 | 74.75 |
|
|
