EDA_GNN: End-to-end Data Association with Graph Neural Network for Online Multiple-Object Tracking
ETH-Jelmoli
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Rendering of new sequences is currently deactivated due to heavy load.
Benchmark:
MOT15 |
Short name:
EDA_GNN
Detector:
Public
Description:
n/a
Reference:
Paper ID 2713
Last submitted:
November 15, 2018 (6 years ago)
Published:
November 15, 2018 at 17:07:05 CET
Submissions:
1
Project page / code:
n/a
Open source:
No
Hardware:
NVIDIA TITAN XP
Runtime:
56.4 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 | 21.8 | 27.8 | 23.3 | 65 (9.0) | 290 (40.2) | 11,970 | 34,587 | 43.7 | 69.2 | 19.5 | 28.4 | 21.5 | 61.8 | 33.6 | 53.2 | 74.2 | 2.1 | 1,488 (34.0) | 1,851 (42.4) |
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 | 11.9 | 29.2 | 24.7 | 6 | 11 | 2,646 | 5,442 | 41.5 | 59.4 | 24.9 | 25.1 | 27.5 | 63.7 | 32.2 | 46.1 | 75.5 | 5.3 | 115 | 156 |
| ADL-Rundle-3 | 24.7 | 25.7 | 21.9 | 3 | 9 | 2,243 | 5,246 | 48.4 | 68.7 | 16.1 | 30.1 | 17.0 | 66.6 | 36.8 | 52.2 | 75.0 | 3.6 | 166 | 133 |
| AVG-TownCentre | 13.8 | 32.7 | 26.1 | 22 | 74 | 1,806 | 4,008 | 43.9 | 63.5 | 24.6 | 28.5 | 29.2 | 52.8 | 34.5 | 49.9 | 72.2 | 4.0 | 347 | 419 |
| ETH-Crossing | 20.4 | 31.7 | 24.7 | 3 | 14 | 94 | 693 | 30.9 | 76.7 | 27.5 | 22.5 | 29.4 | 73.9 | 24.6 | 61.0 | 76.5 | 0.4 | 11 | 15 |
| ETH-Jelmoli | 35.6 | 42.8 | 31.9 | 11 | 14 | 423 | 1,144 | 54.9 | 76.7 | 28.7 | 35.7 | 31.2 | 66.1 | 42.0 | 58.7 | 76.6 | 1.0 | 66 | 62 |
| ETH-Linthescher | 20.3 | 25.8 | 21.7 | 8 | 137 | 330 | 6,700 | 25.0 | 87.1 | 25.6 | 18.5 | 28.2 | 67.8 | 19.3 | 67.5 | 76.7 | 0.3 | 87 | 96 |
| KITTI-16 | 28.5 | 26.6 | 20.0 | 0 | 2 | 285 | 819 | 51.9 | 75.6 | 11.4 | 35.3 | 12.3 | 49.6 | 40.6 | 59.2 | 74.8 | 1.4 | 113 | 117 |
| KITTI-19 | 11.1 | 27.4 | 22.6 | 3 | 19 | 1,628 | 2,948 | 44.8 | 59.5 | 18.9 | 27.5 | 21.0 | 55.3 | 34.5 | 45.8 | 70.8 | 1.5 | 175 | 293 |
| PETS09-S2L2 | 36.5 | 23.8 | 19.9 | 2 | 2 | 1,254 | 4,577 | 52.5 | 80.2 | 11.3 | 35.8 | 11.9 | 58.7 | 39.8 | 60.7 | 73.0 | 2.9 | 289 | 406 |
| TUD-Crossing | 59.2 | 36.8 | 31.2 | 5 | 2 | 105 | 298 | 73.0 | 88.4 | 19.9 | 49.4 | 21.5 | 61.4 | 55.1 | 66.8 | 76.5 | 0.5 | 47 | 35 |
| Venice-1 | 13.7 | 21.8 | 20.1 | 2 | 6 | 1,156 | 2,712 | 40.6 | 61.6 | 16.2 | 25.4 | 17.3 | 62.7 | 31.6 | 48.0 | 74.5 | 2.6 | 72 | 119 |
Raw data:
