MCF_PHD:
TUD-Crossing
Benchmark:
Short name:
MCF_PHD
Detector:
Public
Description:
n/a
Reference:
N. Wojke, D. Paulus. Global data association for the Probability Hypothesis Density filter using network flows. In 2016 IEEE International Conference on Robotics and Automation, ICRA, 2016.
Last submitted:
November 18, 2017 (3 years ago)
Published:
November 18, 2017 at 14:22:51 CET
Submissions:
1
Project page / code:
n/a
Open source:
No
Hardware:
Intel(R) Core(TM) i7-7700HQ CPU @ 2.80GHz
Runtime:
12.2 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| 2D MOT 2015 | 29.9 | 38.2 | 71.7 | 86 (11.9) | 317 (44.0) | 8,892 | 33,529 | 45.4 | 75.8 | 1.5 | 656 (14.4) | 989 (21.8) |
Detailed performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| ADL-Rundle-1 | 14.8 | 35.0 | 72.5 | 8 | 9 | 3,170 | 4,676 | 49.8 | 59.4 | 6.3 | 83 | 105 |
| ADL-Rundle-3 | 33.6 | 39.3 | 73.5 | 4 | 11 | 1,074 | 5,595 | 45.0 | 81.0 | 1.7 | 81 | 85 |
| AVG-TownCentre | 25.7 | 44.2 | 70.1 | 34 | 98 | 1,099 | 4,135 | 42.2 | 73.3 | 2.4 | 77 | 181 |
| ETH-Crossing | -12.7 | 9.5 | 66.6 | 0 | 23 | 209 | 915 | 8.8 | 29.6 | 1.0 | 6 | 6 |
| ETH-Jelmoli | 39.9 | 55.0 | 74.1 | 9 | 14 | 464 | 1,034 | 59.2 | 76.4 | 1.1 | 28 | 48 |
| ETH-Linthescher | 22.6 | 30.7 | 76.2 | 11 | 137 | 130 | 6,746 | 24.5 | 94.4 | 0.1 | 32 | 41 |
| KITTI-16 | 46.4 | 59.2 | 73.6 | 1 | 3 | 114 | 783 | 54.0 | 89.0 | 0.5 | 14 | 26 |
| KITTI-19 | 29.0 | 44.2 | 65.8 | 4 | 13 | 1,029 | 2,708 | 49.3 | 71.9 | 1.0 | 59 | 172 |
| PETS09-S2L2 | 51.8 | 34.7 | 70.1 | 8 | 2 | 694 | 3,744 | 61.2 | 89.5 | 1.6 | 209 | 248 |
| TUD-Crossing | 65.4 | 52.7 | 74.3 | 6 | 2 | 35 | 326 | 70.4 | 95.7 | 0.2 | 20 | 21 |
| Venice-1 | 17.0 | 28.4 | 72.2 | 1 | 5 | 874 | 2,867 | 37.2 | 66.0 | 1.9 | 47 | 56 |
Raw data:
