GSCR: Tracking using global sparse collaborative representations
TUD-Crossing
Benchmark:
Short name:
GSCR
Detector:
Public
Description:
n/a
Reference:
L. Fagot-Bouquet, R. Audigier, Y. Dhome, F. Lerasle. Online multi-person tracking based on global sparse collaborative representations. In ICIP, 2015.
Last submitted:
March 08, 2016 (4 years ago)
Published:
March 15, 2016 at 02:58:15 CET
Submissions:
2
Project page / code:
n/a
Open source:
No
Hardware:
2.7 GHZ, 8 Core
Runtime:
28.1 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| 2D MOT 2015 | 15.8 | 27.9 | 69.4 | 13 (1.8) | 440 (61.0) | 7,597 | 43,633 | 29.0 | 70.1 | 1.3 | 514 (17.7) | 1,010 (34.8) |
Detailed performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| ADL-Rundle-1 | -1.1 | 25.7 | 68.5 | 2 | 12 | 3,165 | 6,179 | 33.6 | 49.7 | 6.3 | 65 | 134 |
| ADL-Rundle-3 | 31.4 | 33.1 | 73.1 | 2 | 12 | 861 | 6,024 | 40.7 | 82.8 | 1.4 | 90 | 83 |
| AVG-TownCentre | 16.5 | 32.6 | 67.8 | 6 | 142 | 437 | 5,488 | 23.2 | 79.2 | 1.0 | 42 | 146 |
| ETH-Crossing | 6.2 | 9.2 | 73.8 | 0 | 23 | 10 | 929 | 7.4 | 88.1 | 0.0 | 2 | 3 |
| ETH-Jelmoli | 22.3 | 38.5 | 69.7 | 1 | 19 | 296 | 1,653 | 34.8 | 74.9 | 0.7 | 22 | 55 |
| ETH-Linthescher | 5.6 | 12.8 | 68.0 | 1 | 171 | 251 | 8,164 | 8.6 | 75.3 | 0.2 | 16 | 53 |
| KITTI-16 | 23.8 | 37.8 | 70.9 | 0 | 6 | 96 | 1,185 | 30.3 | 84.3 | 0.5 | 16 | 31 |
| KITTI-19 | 12.5 | 31.5 | 65.1 | 1 | 29 | 1,024 | 3,594 | 32.7 | 63.1 | 1.0 | 59 | 170 |
| PETS09-S2L2 | 24.1 | 26.8 | 67.6 | 0 | 12 | 946 | 6,214 | 35.5 | 78.4 | 2.2 | 162 | 275 |
| TUD-Crossing | 35.2 | 44.2 | 72.7 | 0 | 3 | 70 | 628 | 43.0 | 87.1 | 0.3 | 16 | 22 |
| Venice-1 | 11.5 | 24.6 | 71.3 | 0 | 11 | 441 | 3,575 | 21.7 | 69.1 | 1.0 | 24 | 38 |
Raw data:
