Benchmark:
MOTS |
Short name:
GMPHD_MAF
Description:
Reference:
Y. Song, Y. Yoon, K. Yoon, M. Jeon, S. Lee, W. Pedrycz. Online Multi-Object Tracking and Segmentation with GMPHD Filter and Mask-based Affinity Fusion. In [Online]. Available: arXiv:2009.00100, 2021.
Last submitted:
April 22, 2021 (3 years ago)
Published:
December 06, 2020 at 15:06:43 CET
Submissions:
4
Project page / code:
Open source:
Yes
Hardware:
Intel i7-7700K @ 4.2GHz, 4 Cores
Runtime:
2.6 Hz
Benchmark performance:
Sequence | sMOTSA | IDF1 | MOTSA | MOTSP | MODSA | MT | ML | TP | FP | FN | Rcll | Prcn | ID Sw. | Frag |
MOTS | 69.4 | 66.4 | 83.3 | 84.2 | 84.8 | 249 (75.9) | 11 (3.4) | 28,284 | 935 | 3,985 | 87.7 | 96.8 | 484 (552.2) | 711 (811.2) |
Detailed performance:
Sequence | sMOTSA | IDF1 | MOTSA | MOTSP | MODSA | MT | ML | TP | FP | FN | Rcll | Prcn | ID Sw. | Frag |
MOTS20-01 | 69.4 | 74.2 | 84.7 | 82.5 | 85.0 | 9 | 0 | 2,725 | 84 | 381 | 87.7 | 97.0 | 11 | 57 |
MOTS20-06 | 73.7 | 66.6 | 87.3 | 85.4 | 90.5 | 156 | 4 | 9,124 | 242 | 690 | 93.0 | 97.4 | 310 | 352 |
MOTS20-07 | 65.3 | 59.0 | 80.6 | 81.9 | 81.5 | 36 | 4 | 10,843 | 353 | 2,035 | 84.2 | 96.8 | 116 | 222 |
MOTS20-12 | 70.9 | 77.1 | 81.7 | 87.4 | 82.5 | 48 | 3 | 5,592 | 256 | 879 | 86.4 | 95.6 | 47 | 80 |
Raw data: