Benchmark:
MOT16 |
Short name:
YOONKJ16
Detector:
Public
Description:
n/a
Reference:
K. YOON, J. GWAK, Y. SONG, Y. YOON, M. JEON. OneShotDA: Online Multi-object Tracker with One-shot-learning-based Data Association. In IEEE Access, 2020.
Last submitted:
August 01, 2019 (3 years ago)
Published:
August 10, 2019 at 10:49:14 CET
Submissions:
4
Project page / code:
n/a
Open source:
No
Hardware:
i7_GTX1080ti
Runtime:
3.5 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| MOT16 | 47.0 | 50.1 | 38.5 | 125 (16.5) | 317 (41.8) | 7,901 | 88,179 | 51.6 | 92.3 | 39.0 | 38.3 | 43.3 | 71.1 | 40.7 | 72.7 | 79.0 | 1.3 | 627 (12.1) | 945 (18.3) |
Detailed performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| MOT16-01 | 37.0 | 33.7 | 26.5 | 5 | 10 | 260 | 3,736 | 41.6 | 91.1 | 24.2 | 29.2 | 33.7 | 48.5 | 30.9 | 67.6 | 76.0 | 0.6 | 32 | 54 |
| MOT16-03 | 54.4 | 54.1 | 41.5 | 34 | 26 | 4,101 | 43,274 | 58.6 | 93.7 | 39.9 | 43.5 | 43.1 | 73.5 | 46.2 | 73.8 | 79.1 | 2.7 | 281 | 460 |
| MOT16-06 | 46.7 | 53.8 | 40.4 | 45 | 109 | 747 | 5,337 | 53.7 | 89.2 | 43.2 | 38.2 | 56.3 | 59.3 | 41.5 | 68.9 | 77.8 | 0.6 | 70 | 98 |
| MOT16-07 | 41.6 | 43.2 | 32.8 | 6 | 17 | 770 | 8,680 | 46.8 | 90.8 | 31.6 | 34.3 | 34.3 | 68.1 | 36.4 | 70.7 | 78.0 | 1.5 | 88 | 121 |
| MOT16-08 | 32.6 | 40.5 | 33.9 | 12 | 22 | 1,086 | 10,114 | 39.6 | 85.9 | 37.5 | 30.8 | 42.1 | 71.5 | 33.1 | 71.9 | 81.3 | 1.7 | 82 | 90 |
| MOT16-12 | 42.3 | 53.0 | 40.9 | 13 | 38 | 443 | 4,321 | 47.9 | 90.0 | 46.9 | 35.8 | 54.2 | 66.5 | 38.4 | 72.1 | 80.2 | 0.5 | 24 | 38 |
| MOT16-14 | 28.3 | 40.3 | 29.4 | 10 | 95 | 494 | 12,717 | 31.2 | 92.1 | 37.0 | 23.5 | 39.5 | 72.2 | 24.4 | 72.1 | 78.2 | 0.7 | 50 | 84 |
Raw data: