Benchmark:
MOT16 |
Short name:
GM_PHD_DAL
Detector:
Public
Description:
n/a
Reference:
N. Baisa. Online Multi-object Visual Tracking using a GM-PHD Filter with Deep Appearance Learning. In 2019 22th International Conference on Information Fusion (FUSION), 2019.
Last submitted:
March 21, 2019 (5 years ago)
Published:
February 11, 2019 at 22:59:20 CET
Submissions:
2
Project page / code:
Open source:
No
Hardware:
3 GHZ, 1 Core
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 | 35.1 | 26.6 | 23.0 | 53 (7.0) | 390 (51.4) | 2,350 | 111,886 | 38.6 | 96.8 | 18.3 | 29.3 | 19.5 | 69.7 | 30.3 | 75.8 | 79.9 | 0.4 | 4,047 (104.8) | 5,338 (138.2) |
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 | 22.0 | 19.7 | 17.7 | 2 | 13 | 63 | 4,818 | 24.7 | 96.2 | 17.3 | 18.2 | 18.2 | 64.0 | 18.6 | 72.6 | 77.8 | 0.1 | 107 | 170 |
| MOT16-03 | 40.9 | 27.4 | 23.9 | 12 | 44 | 1,009 | 58,348 | 44.2 | 97.9 | 17.2 | 33.5 | 18.0 | 73.0 | 34.6 | 76.6 | 80.0 | 0.7 | 2,393 | 3,121 |
| MOT16-06 | 40.2 | 36.8 | 28.5 | 18 | 112 | 125 | 6,457 | 44.0 | 97.6 | 25.4 | 32.3 | 30.4 | 56.7 | 33.4 | 74.1 | 78.2 | 0.1 | 313 | 371 |
| MOT16-07 | 29.5 | 23.6 | 20.1 | 4 | 26 | 332 | 10,710 | 34.4 | 94.4 | 15.9 | 25.8 | 16.6 | 61.5 | 26.7 | 73.3 | 78.5 | 0.7 | 472 | 638 |
| MOT16-08 | 28.5 | 25.3 | 22.6 | 5 | 29 | 237 | 11,498 | 31.3 | 95.7 | 20.4 | 25.1 | 21.8 | 68.2 | 25.9 | 79.0 | 82.6 | 0.4 | 229 | 310 |
| MOT16-12 | 36.0 | 34.8 | 28.5 | 8 | 44 | 313 | 4,842 | 41.6 | 91.7 | 25.9 | 31.4 | 27.9 | 71.9 | 33.2 | 73.1 | 80.5 | 0.3 | 155 | 230 |
| MOT16-14 | 14.2 | 15.6 | 13.7 | 4 | 122 | 271 | 15,213 | 17.7 | 92.3 | 14.1 | 13.4 | 15.7 | 57.7 | 13.7 | 71.5 | 78.7 | 0.4 | 378 | 498 |
Raw data: