SAS_MOT15:
ETH-Crossing
Benchmark:
MOT15 |
Short name:
SAS_MOT15
Detector:
Public
Description:
n/a
Reference:
A. Maksai, P. Fua. Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking. In CVPR, 2019.
Last submitted:
May 03, 2018 (2 years ago)
Published:
May 14, 2019 at 21:14:35 CET
Submissions:
1
Project page / code:
n/a
Open source:
No
Hardware:
2.5 GHZ, 1 Core
Runtime:
8.9 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| MOT15 | 22.2 | 27.2 | 71.1 | 22 (3.1) | 444 (61.6) | 5,591 | 41,531 | 32.4 | 78.1 | 1.0 | 700 (21.6) | 1,240 (38.3) |
Detailed performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| ADL-Rundle-1 | 14.7 | 26.8 | 71.8 | 4 | 8 | 2,592 | 5,203 | 44.1 | 61.3 | 5.2 | 143 | 254 |
| ADL-Rundle-3 | 32.3 | 34.0 | 72.8 | 4 | 14 | 875 | 5,891 | 42.1 | 83.0 | 1.4 | 120 | 130 |
| AVG-TownCentre | 9.2 | 11.7 | 69.6 | 0 | 178 | 195 | 6,277 | 12.2 | 81.7 | 0.4 | 19 | 53 |
| ETH-Crossing | 15.2 | 22.3 | 73.8 | 0 | 20 | 13 | 834 | 16.8 | 92.9 | 0.1 | 4 | 6 |
| ETH-Jelmoli | 38.3 | 41.9 | 71.9 | 6 | 15 | 320 | 1,209 | 52.3 | 80.6 | 0.7 | 37 | 61 |
| ETH-Linthescher | 15.7 | 19.5 | 73.1 | 3 | 155 | 129 | 7,360 | 17.6 | 92.4 | 0.1 | 36 | 52 |
| KITTI-16 | 34.9 | 43.9 | 72.4 | 0 | 3 | 130 | 951 | 44.1 | 85.2 | 0.6 | 26 | 46 |
| KITTI-19 | 18.7 | 32.8 | 65.4 | 2 | 24 | 691 | 3,590 | 32.8 | 71.7 | 0.7 | 65 | 233 |
| PETS09-S2L2 | 27.2 | 22.1 | 68.7 | 0 | 14 | 528 | 6,292 | 34.7 | 86.4 | 1.2 | 198 | 310 |
| TUD-Crossing | 59.2 | 50.3 | 73.5 | 3 | 2 | 25 | 401 | 63.6 | 96.6 | 0.1 | 24 | 40 |
| Venice-1 | 20.1 | 25.6 | 72.7 | 0 | 11 | 93 | 3,523 | 22.8 | 91.8 | 0.2 | 28 | 55 |
Raw data:
