Research Article
Pillar-Based 3D Object Detection from Point Cloud with Multiattention Mechanism
Table 6
Results on the KITTI test BEV detection benchmark.
| | Model | Car | Pedestrian | Cyclist | | Easy (%) | Mod. (%) | Hard (%) | mAP (%) | Easy (%) | Mod. (%) | Hard (%) | mAP (%) | Easy (%) | Mod. (%) | Hard (%) | mAP (%) |
| | PointPillars | 88.35 | 86.10 | 79.83 | 84.76 | 58.66 | 50.23 | 47.19 | 52.02 | 79.14 | 62.25 | 56.00 | 65.79 | | PointPillars + channel attention | 89.38 | 85.39 | 83.43 | 86.06 | 57.38 | 51.84 | 48.12 | 52.44 | 79.62 | 63.59 | 60.38 | 67.86 | | PointPillars + SOCA | 89.50 | 86.30 | 83.80 | 86.53 | 58.37 | 53.07 | 49.18 | 53.54 | 81.26 | 64.75 | 61.87 | 69.29 |
|
|
