Research Article
3D Semantic VSLAM of Dynamic Environment Based on YOLACT
Table 1
Comparison of speed and precision between YOLACT and other algorithms.
| | Method | Backbone | FPS | Time | AP | AP50 | AP75 | APS | APM | APL |
| | PA-net [27] | R-50-FPN | 4.7 | 212.8 | 36.6 | 58.0 | 39.3 | 16.3 | 38.1 | 53.1 | | FCIS [28] | R-101-FPN | 6.6 | 151.5 | 29.5 | 51.5 | 30.2 | 8.0 | 31.0 | 49.7 | | Mask R-CNN [21] | R-101-FPN | 8.6 | 116.3 | 35.7 | 58.0 | 37.8 | 15.5 | 38.1 | 52.4 | | MS R-CNN [22] | R-101-FPN | 8.6 | 116.3 | 38.3 | 58.8 | 41.5 | 17.8 | 40.4 | 54.4 | | YOLACT | R-101-FPN | 38.6 | 24.6 | 28.5 | 46.9 | 29.9 | 9.5 | 30.1 | 45.5 |
|
|
