TO: Leveraging single for multi-target tracking using a novel trajectory overlap affinity measure
TUD-Crossing
Benchmark:
Short name:
TO
Detector:
Public
Description:
n/a
Reference:
S. Manen, R. Timofte, D. Dai, L. Gool. Leveraging single for multi-target tracking using a novel trajectory overlap affinity measure. In 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), 2016.
Last submitted:
September 02, 2015 (5 years ago)
Published:
April 19, 2017 at 14:44:27 CET
Submissions:
1
Project page / code:
n/a
Open source:
No
Hardware:
1.6 GHZ, 8 Cores
Runtime:
5.0 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| 2D MOT 2015 | 25.7 | 32.7 | 72.2 | 31 (4.3) | 414 (57.4) | 4,779 | 40,511 | 34.1 | 81.4 | 0.8 | 383 (11.2) | 600 (17.6) |
Detailed performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| ADL-Rundle-1 | 17.9 | 38.4 | 73.4 | 6 | 10 | 2,336 | 5,270 | 43.4 | 63.3 | 4.7 | 33 | 49 |
| ADL-Rundle-3 | 31.6 | 36.2 | 74.1 | 2 | 13 | 683 | 6,216 | 38.9 | 85.3 | 1.1 | 51 | 50 |
| AVG-TownCentre | 18.8 | 25.9 | 70.0 | 6 | 139 | 209 | 5,533 | 22.6 | 88.5 | 0.5 | 63 | 131 |
| ETH-Crossing | 16.7 | 22.6 | 76.5 | 0 | 19 | 2 | 830 | 17.2 | 98.9 | 0.0 | 4 | 4 |
| ETH-Jelmoli | 32.8 | 43.0 | 75.1 | 6 | 19 | 139 | 1,559 | 38.5 | 87.6 | 0.3 | 7 | 21 |
| ETH-Linthescher | 8.3 | 13.3 | 77.3 | 1 | 172 | 24 | 8,162 | 8.6 | 97.0 | 0.0 | 7 | 8 |
| KITTI-16 | 39.9 | 48.0 | 74.4 | 0 | 2 | 64 | 951 | 44.1 | 92.1 | 0.3 | 7 | 20 |
| KITTI-19 | 32.2 | 43.8 | 65.7 | 4 | 21 | 451 | 3,137 | 41.3 | 83.0 | 0.4 | 32 | 113 |
| PETS09-S2L2 | 40.7 | 30.7 | 70.6 | 3 | 8 | 522 | 5,049 | 47.6 | 89.8 | 1.2 | 145 | 168 |
| TUD-Crossing | 57.2 | 51.5 | 73.1 | 3 | 3 | 26 | 429 | 61.1 | 96.3 | 0.1 | 17 | 17 |
| Venice-1 | 18.6 | 25.2 | 74.4 | 0 | 8 | 323 | 3,375 | 26.0 | 78.6 | 0.7 | 17 | 19 |
Raw data:
