INARLA:
TUD-Crossing
Benchmark:
MOT15 |
Short name:
INARLA
Detector:
Public
Description:
n/a
Reference:
H. Wu, Y. Hu, K. Wang, H. Li, L. Nie, H. Cheng. Instance-aware representation learning and association for online multi-person tracking. In Pattern Recognition, 2019.
Last submitted:
February 11, 2018 (3 years ago)
Published:
August 09, 2019 at 10:02:30 CET
Submissions:
1
Project page / code:
n/a
Open source:
No
Hardware:
CPU: 8 core, 3.7 GHz, GPU: Tesla K40
Runtime:
2.6 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| MOT15 | 34.7 | 42.1 | 31.8 | 90 (12.5) | 216 (30.0) | 9,855 | 29,158 | 52.5 | 76.6 | 29.5 | 34.5 | 33.0 | 63.3 | 40.0 | 58.3 | 74.8 | 1.7 | 1,112 (21.2) | 2,848 (54.2) |
Detailed performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| ADL-Rundle-1 | 20.1 | 42.1 | 31.8 | 6 | 3 | 3,463 | 3,868 | 58.4 | 61.1 | 30.8 | 32.9 | 34.1 | 62.3 | 44.5 | 46.5 | 73.5 | 6.9 | 100 | 402 |
| ADL-Rundle-3 | 36.0 | 37.8 | 29.7 | 7 | 8 | 1,383 | 5,014 | 50.7 | 78.8 | 25.1 | 35.3 | 27.7 | 65.1 | 40.3 | 62.7 | 77.5 | 2.2 | 109 | 221 |
| AVG-TownCentre | 32.1 | 45.7 | 32.4 | 20 | 54 | 955 | 3,649 | 49.0 | 78.6 | 32.4 | 33.0 | 36.4 | 61.9 | 36.7 | 58.8 | 72.4 | 2.1 | 250 | 570 |
| ETH-Crossing | 35.2 | 48.5 | 33.1 | 2 | 11 | 72 | 566 | 43.6 | 85.9 | 34.3 | 32.1 | 36.8 | 72.3 | 34.6 | 68.1 | 78.1 | 0.3 | 12 | 22 |
| ETH-Jelmoli | 48.1 | 57.1 | 40.9 | 13 | 13 | 329 | 955 | 62.4 | 82.8 | 40.9 | 40.9 | 48.7 | 62.7 | 47.4 | 63.0 | 77.8 | 0.7 | 33 | 76 |
| ETH-Linthescher | 41.3 | 48.3 | 35.7 | 20 | 104 | 472 | 4,704 | 47.3 | 90.0 | 37.3 | 34.2 | 41.0 | 69.0 | 36.5 | 69.3 | 77.2 | 0.4 | 69 | 164 |
| KITTI-16 | 32.9 | 55.0 | 36.7 | 0 | 1 | 329 | 786 | 53.8 | 73.6 | 38.8 | 34.7 | 42.6 | 60.1 | 40.1 | 54.9 | 71.7 | 1.6 | 26 | 113 |
| KITTI-19 | 24.4 | 46.9 | 33.3 | 7 | 15 | 1,324 | 2,649 | 50.4 | 67.0 | 33.7 | 33.1 | 37.7 | 60.0 | 39.3 | 52.3 | 71.5 | 1.3 | 67 | 326 |
| PETS09-S2L2 | 40.5 | 26.1 | 20.5 | 3 | 5 | 703 | 4,657 | 51.7 | 87.6 | 12.0 | 35.2 | 13.7 | 55.2 | 38.1 | 64.6 | 74.4 | 1.6 | 380 | 743 |
| TUD-Crossing | 73.0 | 63.3 | 45.8 | 7 | 0 | 12 | 260 | 76.4 | 98.6 | 39.3 | 53.4 | 43.0 | 66.7 | 56.5 | 72.9 | 77.8 | 0.1 | 25 | 51 |
| Venice-1 | 36.4 | 40.1 | 31.3 | 5 | 2 | 813 | 2,050 | 55.1 | 75.6 | 29.1 | 33.9 | 33.7 | 62.5 | 40.2 | 55.2 | 74.3 | 1.8 | 41 | 160 |
Raw data:
