Benchmark:
MOT16 |
Short name:
CDA_DDALv2
Detector:
Public
Description:
n/a
Reference:
S. Bae and K. Yoon, Confidence-Based Data Association and Discriminative Deep Appearance Learning for Robust Online Multi-Object Tracking , In IEEE TPAMI, 2017.
Last submitted:
February 21, 2017 (7 years ago)
Published:
March 05, 2017 at 02:30:03 CET
Submissions:
1
Project page / code:
n/a
Open source:
No
Hardware:
3.1GHz, 1 Core
Runtime:
0.5 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 | 43.9 | 45.1 | 34.0 | 81 (10.7) | 337 (44.4) | 6,450 | 95,175 | 47.8 | 93.1 | 33.1 | 35.1 | 35.8 | 69.0 | 37.1 | 72.2 | 78.2 | 1.1 | 676 (14.1) | 1,795 (37.6) |
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 | 33.2 | 38.8 | 28.4 | 4 | 10 | 156 | 4,098 | 35.9 | 93.6 | 32.1 | 25.2 | 35.4 | 64.0 | 26.2 | 68.4 | 75.5 | 0.3 | 21 | 79 |
| MOT16-03 | 51.8 | 48.8 | 36.7 | 27 | 31 | 3,029 | 47,087 | 55.0 | 95.0 | 33.3 | 40.6 | 35.7 | 70.1 | 42.7 | 73.7 | 78.6 | 2.0 | 251 | 890 |
| MOT16-06 | 39.2 | 44.3 | 32.7 | 20 | 112 | 798 | 6,119 | 47.0 | 87.2 | 32.7 | 32.8 | 42.0 | 52.9 | 35.7 | 66.2 | 76.8 | 0.7 | 93 | 170 |
| MOT16-07 | 38.8 | 43.7 | 32.1 | 6 | 17 | 810 | 9,064 | 44.5 | 90.0 | 32.5 | 31.8 | 34.6 | 67.6 | 33.8 | 68.4 | 76.3 | 1.6 | 107 | 258 |
| MOT16-08 | 28.9 | 32.3 | 26.5 | 4 | 28 | 503 | 11,322 | 32.3 | 91.5 | 27.9 | 25.3 | 29.5 | 74.6 | 26.3 | 74.6 | 80.8 | 0.8 | 79 | 128 |
| MOT16-12 | 38.3 | 47.1 | 38.0 | 14 | 50 | 474 | 4,615 | 44.4 | 88.6 | 43.9 | 32.8 | 46.3 | 75.5 | 35.2 | 70.4 | 79.2 | 0.5 | 27 | 52 |
| MOT16-14 | 26.2 | 35.5 | 25.1 | 6 | 89 | 680 | 12,870 | 30.4 | 89.2 | 28.3 | 22.3 | 30.5 | 64.1 | 23.3 | 68.5 | 76.7 | 0.9 | 98 | 218 |
Raw data: