FGRNetIV: Flow-guided Geometric Regression Network with Identity Verification
TUD-Crossing
Short name:
FGRNetIV
Detector:
Public
Description:
Reference:
Last submitted:
December 15, 2020 (2 months ago)
Published:
December 15, 2020 at 12:41:19 CET
Submissions:
1
Project page / code:
n/a
Open source:
No
Hardware:
2080Ti
Runtime:
1.4 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| MOT15 | 47.5 | 47.8 | 76.1 | 169 (23.4) | 190 (26.4) | 5,531 | 25,502 | 58.5 | 86.7 | 1.0 | 1,240 (21.2) | 1,550 (26.5) |
Detailed performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| ADL-Rundle-1 | 38.8 | 50.7 | 74.2 | 11 | 4 | 2,103 | 3,533 | 62.0 | 73.3 | 4.2 | 60 | 162 |
| ADL-Rundle-3 | 47.6 | 48.4 | 81.7 | 8 | 7 | 537 | 4,723 | 53.5 | 91.0 | 0.9 | 68 | 79 |
| AVG-TownCentre | 47.1 | 46.3 | 71.1 | 70 | 35 | 916 | 2,370 | 66.8 | 83.9 | 2.0 | 498 | 453 |
| ETH-Crossing | 43.4 | 49.5 | 83.8 | 3 | 10 | 31 | 519 | 48.3 | 94.0 | 0.1 | 18 | 17 |
| ETH-Jelmoli | 57.7 | 63.9 | 80.5 | 15 | 13 | 301 | 741 | 70.8 | 85.6 | 0.7 | 32 | 44 |
| ETH-Linthescher | 50.3 | 55.3 | 80.7 | 32 | 96 | 217 | 4,161 | 53.4 | 95.6 | 0.2 | 59 | 89 |
| KITTI-16 | 51.3 | 55.2 | 70.5 | 3 | 1 | 101 | 693 | 59.3 | 90.9 | 0.5 | 34 | 54 |
| KITTI-19 | 46.7 | 53.0 | 71.8 | 10 | 17 | 457 | 2,244 | 58.0 | 87.1 | 0.4 | 146 | 145 |
| PETS09-S2L2 | 48.8 | 29.8 | 74.9 | 2 | 4 | 283 | 4,383 | 54.5 | 94.9 | 0.6 | 274 | 438 |
| TUD-Crossing | 77.6 | 53.4 | 74.8 | 9 | 0 | 15 | 213 | 80.7 | 98.3 | 0.1 | 19 | 25 |
| Venice-1 | 44.7 | 44.7 | 75.4 | 6 | 3 | 570 | 1,922 | 57.9 | 82.2 | 1.3 | 32 | 44 |
Raw data:
