KCF:
TUD-Crossing
Benchmark:
Short name:
KCF
Detector:
Public
Description:
n/a
Reference:
P. Chu, H. Fan, C. Tan, H. Ling. Online Multi-Object Tracking with Instance-Aware Tracker and Dynamic Model Refreshment. In WACV, 2019.
Last submitted:
February 21, 2018 (2 years ago)
Published:
February 25, 2019 at 21:33:19 CET
Submissions:
3
Project page / code:
n/a
Open source:
No
Hardware:
i7 3.6GHz, 4 Core
Runtime:
0.3 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| 2D MOT 2015 | 38.9 | 44.5 | 70.6 | 120 (16.6) | 227 (31.5) | 7,321 | 29,501 | 52.0 | 81.4 | 1.3 | 720 (13.9) | 1,440 (27.7) |
Detailed performance:
| Sequence | MOTA | IDF1 | MOTP | MT | ML | FP | FN | Recall | Precision | FAF | ID Sw. | Frag |
| ADL-Rundle-1 | 25.6 | 37.8 | 70.9 | 3 | 5 | 2,197 | 4,649 | 50.0 | 67.9 | 4.4 | 81 | 168 |
| ADL-Rundle-3 | 43.0 | 44.0 | 72.5 | 7 | 7 | 639 | 5,059 | 50.2 | 88.9 | 1.0 | 96 | 116 |
| AVG-TownCentre | 40.1 | 54.2 | 68.5 | 55 | 38 | 1,240 | 2,860 | 60.0 | 77.6 | 2.8 | 182 | 431 |
| ETH-Crossing | 31.5 | 50.2 | 74.0 | 3 | 13 | 53 | 632 | 37.0 | 87.5 | 0.2 | 2 | 4 |
| ETH-Jelmoli | 50.4 | 57.7 | 71.7 | 14 | 14 | 350 | 882 | 65.2 | 82.5 | 0.8 | 26 | 65 |
| ETH-Linthescher | 28.2 | 37.0 | 72.0 | 14 | 122 | 334 | 6,021 | 32.6 | 89.7 | 0.3 | 60 | 127 |
| KITTI-16 | 53.0 | 65.2 | 72.5 | 3 | 2 | 140 | 645 | 62.1 | 88.3 | 0.7 | 14 | 26 |
| KITTI-19 | 33.7 | 54.1 | 66.0 | 5 | 19 | 787 | 2,727 | 49.0 | 76.9 | 0.7 | 27 | 256 |
| PETS09-S2L2 | 51.8 | 37.9 | 68.8 | 7 | 1 | 1,045 | 3,418 | 64.5 | 85.6 | 2.4 | 181 | 193 |
| TUD-Crossing | 76.0 | 69.1 | 75.1 | 6 | 0 | 8 | 248 | 77.5 | 99.1 | 0.0 | 8 | 10 |
| Venice-1 | 35.8 | 36.3 | 73.6 | 3 | 6 | 528 | 2,360 | 48.3 | 80.7 | 1.2 | 43 | 44 |
Raw data:
