Benchmark:
MOTS |
Short name:
OPITrack_
Description:
Y. Gao, H. Xu, Y. Zheng, J. Li and X. Gao, "An Object Point Set Inductive Tracker for Multi-Object Tracking and Segmentation," in IEEE Transactions on Image Processing, 2022, doi: 10.1109/TIP.2022.3203607.
Reference:
Y. Gao, H. Xu, Y. Zheng, J. Li and X. Gao, "An Object Point Set Inductive Tracker for Multi-Object Tracking and Segmentation," in IEEE Transactions on Image Processing, 2022, doi: 10.1109/TIP.2022.3203607.
Last submitted:
July 13, 2021 (3 years ago)
Published:
September 11, 2022 at 14:42:01 CET
Submissions:
1
Project page / code:
n/a
Open source:
No
Hardware:
GPU
Runtime:
3,382.2 Hz
Benchmark performance:
| Sequence | sMOTSA | IDF1 | MOTSA | MOTSP | MODSA | MT | ML | TP | FP | FN | Rcll | Prcn | ID Sw. | Frag |
| MOTS | 63.5 | 45.4 | 75.5 | 84.6 | 76.6 | 218 (66.5) | 28 (8.5) | 25,152 | 441 | 7,117 | 77.9 | 98.3 | 342 (438.8) | 583 (748.0) |
Detailed performance:
| Sequence | sMOTSA | IDF1 | MOTSA | MOTSP | MODSA | MT | ML | TP | FP | FN | Rcll | Prcn | ID Sw. | Frag |
| MOTS20-01 | 68.5 | 60.3 | 82.8 | 83.1 | 83.7 | 8 | 0 | 2,617 | 16 | 489 | 84.3 | 99.4 | 29 | 53 |
| MOTS20-06 | 74.4 | 31.5 | 88.0 | 85.1 | 89.4 | 148 | 9 | 8,936 | 158 | 878 | 91.1 | 98.3 | 144 | 222 |
| MOTS20-07 | 49.9 | 46.9 | 60.2 | 83.2 | 61.2 | 13 | 17 | 7,887 | 12 | 4,991 | 61.2 | 99.8 | 125 | 221 |
| MOTS20-12 | 71.6 | 57.4 | 83.7 | 86.3 | 84.3 | 49 | 2 | 5,712 | 255 | 759 | 88.3 | 95.7 | 44 | 87 |
Raw data: