PHD_GSDL: PHD Filter With Online Group-structured Dictionary Learning
TUD-Crossing
Benchmark:
Short name:
PHD_GSDL
Detector:
Public
Description:
n/a
Reference:
Z. Fu, P. Feng, F. Angelini, J. Chambers, S. Naqvi. Particle PHD Filter based Multiple Human Tracking using Online Group-Structured Dictionary Learning. In IEEE Access, 2018.
Last submitted:
August 06, 2017 (3 years ago)
Published:
August 03, 2017 at 20:10:13 CET
Submissions:
4
Project page / code:
n/a
Open source:
No
Hardware:
3.5GHz, 1 Core
Runtime:
8.2 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| 2D MOT 2015 | 30.5 | 38.8 | 71.2 | 55 (7.6) | 297 (41.2) | 6,534 | 35,284 | 42.6 | 80.0 | 1.1 | 879 (20.6) | 2,208 (51.9) |
Detailed performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| ADL-Rundle-1 | 21.9 | 38.1 | 72.7 | 5 | 10 | 1,423 | 5,788 | 37.8 | 71.2 | 2.8 | 54 | 251 |
| ADL-Rundle-3 | 36.7 | 37.2 | 73.0 | 4 | 10 | 904 | 5,407 | 46.8 | 84.0 | 1.4 | 121 | 188 |
| AVG-TownCentre | 27.2 | 47.3 | 68.6 | 18 | 81 | 952 | 4,127 | 42.3 | 76.0 | 2.1 | 127 | 421 |
| ETH-Crossing | 24.6 | 35.9 | 74.6 | 0 | 12 | 50 | 701 | 30.1 | 85.8 | 0.2 | 5 | 18 |
| ETH-Jelmoli | 42.5 | 55.6 | 73.1 | 6 | 14 | 223 | 1,205 | 52.5 | 85.7 | 0.5 | 31 | 68 |
| ETH-Linthescher | 22.9 | 33.9 | 74.0 | 8 | 135 | 256 | 6,592 | 26.2 | 90.1 | 0.2 | 40 | 202 |
| KITTI-16 | 39.4 | 49.7 | 72.6 | 0 | 2 | 222 | 770 | 54.7 | 80.7 | 1.1 | 38 | 104 |
| KITTI-19 | 21.6 | 41.6 | 66.8 | 3 | 19 | 973 | 3,122 | 41.6 | 69.5 | 0.9 | 96 | 258 |
| PETS09-S2L2 | 43.6 | 30.4 | 69.1 | 6 | 5 | 987 | 4,144 | 57.0 | 84.8 | 2.3 | 311 | 525 |
| TUD-Crossing | 69.1 | 64.2 | 73.5 | 5 | 1 | 21 | 298 | 73.0 | 97.5 | 0.1 | 21 | 48 |
| Venice-1 | 19.2 | 33.7 | 73.0 | 0 | 8 | 523 | 3,130 | 31.4 | 73.3 | 1.2 | 35 | 125 |
Raw data:
