CDA_DDALpb:
TUD-Crossing
Benchmark:
Short name:
CDA_DDALpb
Detector:
Public
Description:
n/a
Reference:
S. Bae and K. Yoon, Confidence-Based Data Association and Discriminative Deep Appearance Learning for Robust Online Multi-Object Tracking , In IEEE TPAMI, 2017.
Last submitted:
February 26, 2017 (3 years ago)
Published:
March 05, 2017 at 02:29:30 CET
Submissions:
1
Project page / code:
n/a
Open source:
No
Hardware:
3.1GHz, 1 Core
Runtime:
2.3 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| 2D MOT 2015 | 32.8 | 38.8 | 70.7 | 70 (9.7) | 304 (42.2) | 4,983 | 35,690 | 41.9 | 83.8 | 0.9 | 614 (14.7) | 1,583 (37.8) |
Detailed performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| ADL-Rundle-1 | 30.5 | 43.3 | 71.7 | 6 | 9 | 1,064 | 5,365 | 42.3 | 78.7 | 2.1 | 41 | 104 |
| ADL-Rundle-3 | 38.7 | 39.3 | 72.0 | 5 | 15 | 374 | 5,807 | 42.9 | 92.1 | 0.6 | 48 | 81 |
| AVG-TownCentre | 30.7 | 42.7 | 68.9 | 31 | 72 | 1,013 | 3,807 | 46.7 | 76.7 | 2.3 | 136 | 367 |
| ETH-Crossing | 30.9 | 39.7 | 74.0 | 3 | 13 | 37 | 649 | 35.3 | 90.5 | 0.2 | 7 | 12 |
| ETH-Jelmoli | 34.6 | 44.6 | 73.1 | 5 | 20 | 179 | 1,462 | 42.4 | 85.7 | 0.4 | 18 | 48 |
| ETH-Linthescher | 23.3 | 31.8 | 73.3 | 9 | 137 | 228 | 6,570 | 26.4 | 91.2 | 0.2 | 53 | 101 |
| KITTI-16 | 37.2 | 49.0 | 71.3 | 0 | 3 | 262 | 773 | 54.6 | 78.0 | 1.3 | 34 | 120 |
| KITTI-19 | 24.0 | 37.8 | 66.8 | 2 | 21 | 703 | 3,315 | 38.0 | 74.3 | 0.7 | 45 | 218 |
| PETS09-S2L2 | 42.5 | 33.7 | 69.3 | 3 | 3 | 934 | 4,409 | 54.3 | 84.9 | 2.1 | 196 | 438 |
| TUD-Crossing | 62.9 | 60.6 | 72.3 | 4 | 1 | 53 | 347 | 68.5 | 93.4 | 0.3 | 9 | 22 |
| Venice-1 | 26.6 | 31.9 | 70.9 | 2 | 10 | 136 | 3,186 | 30.2 | 91.0 | 0.3 | 27 | 72 |
Raw data:
