Benchmark:
MOT20 |
Short name:
SORT20
Detector:
Public
Description:
SORT is a barebones implementation of a visual multiple object tracking framework based on rudimentary data association and state estimation techniques.
For MOT20 hyper-parameters are set as follows:
max_age=100
min_hits=1
Reference:
A. Bewley, Z. Ge, L. Ott, F. Ramos, B. Upcroft. Simple online and realtime tracking. In 2016 IEEE International Conference on Image Processing (ICIP), 2016.
Last submitted:
May 11, 2020 (4 years ago)
Published:
May 11, 2020 at 16:42:59 CET
Submissions:
1
Project page / code:
Open source:
No
Hardware:
2.5 GHz, 4 cores
Runtime:
57.3 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| MOT20 | 42.7 | 45.1 | 36.1 | 208 (16.7) | 326 (26.2) | 27,521 | 264,694 | 48.8 | 90.2 | 35.9 | 36.7 | 39.4 | 66.9 | 39.5 | 73.0 | 81.0 | 6.1 | 4,470 (91.5) | 17,798 (364.4) |
Detailed performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| MOT20-04 | 59.5 | 56.7 | 44.2 | 139 | 79 | 3,206 | 106,117 | 61.3 | 98.1 | 40.5 | 48.4 | 44.3 | 70.6 | 50.5 | 80.8 | 83.2 | 1.5 | 1,643 | 10,853 |
| MOT20-06 | 23.7 | 29.5 | 23.9 | 26 | 123 | 12,309 | 87,352 | 34.2 | 78.7 | 24.0 | 24.1 | 26.6 | 56.5 | 26.5 | 61.0 | 76.3 | 12.2 | 1,640 | 3,982 |
| MOT20-07 | 48.5 | 47.3 | 36.7 | 30 | 22 | 1,032 | 15,666 | 52.7 | 94.4 | 35.1 | 39.1 | 38.9 | 67.5 | 41.6 | 74.6 | 80.8 | 1.8 | 360 | 872 |
| MOT20-08 | 13.1 | 24.2 | 19.9 | 13 | 102 | 10,974 | 55,559 | 28.3 | 66.6 | 20.6 | 19.5 | 23.1 | 52.7 | 22.1 | 52.1 | 74.3 | 13.6 | 827 | 2,091 |
Raw data: