TC_SIAMESE: Tracker with selective siamese calculation
ETH-Linthescher
Benchmark:
MOT15 |
Short name:
TC_SIAMESE
Detector:
Public
Description:
n/a
Reference:
Y. Yoon, Y. Song, K. Yoon, M. Jeon. Online Multiple-Object Tracking using Selective Deep Appearance Matching. In IEEE/IEIE The International Conference on Consumer Electronics (ICCE) Asia, 2018.
Last submitted:
April 09, 2018 (6 years ago)
Published:
April 02, 2018 at 04:17:21 CET
Submissions:
4
Project page / code:
n/a
Open source:
No
Hardware:
3.7 GHZ, 4 Core
Runtime:
13.0 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| MOT15 | 20.2 | 32.6 | 24.6 | 19 (2.6) | 487 (67.5) | 6,127 | 42,596 | 30.7 | 75.5 | 28.7 | 21.4 | 31.5 | 65.6 | 23.5 | 57.8 | 74.9 | 1.1 | 294 (9.6) | 825 (26.9) |
Detailed performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| ADL-Rundle-1 | 14.6 | 38.6 | 29.0 | 6 | 8 | 2,549 | 5,357 | 42.4 | 60.8 | 33.4 | 25.6 | 36.8 | 67.7 | 32.6 | 46.6 | 75.2 | 5.1 | 42 | 149 |
| ADL-Rundle-3 | 34.9 | 40.1 | 28.4 | 3 | 14 | 699 | 5,866 | 42.3 | 86.0 | 27.2 | 29.8 | 28.8 | 70.9 | 32.1 | 65.3 | 76.4 | 1.1 | 49 | 75 |
| AVG-TownCentre | 3.6 | 12.9 | 12.3 | 1 | 195 | 293 | 6,593 | 7.8 | 65.4 | 25.5 | 6.0 | 29.5 | 55.0 | 6.2 | 52.6 | 72.7 | 0.7 | 7 | 32 |
| ETH-Crossing | 16.0 | 27.3 | 19.8 | 0 | 18 | 56 | 786 | 21.6 | 79.5 | 25.1 | 15.7 | 30.5 | 56.6 | 16.6 | 61.0 | 75.6 | 0.3 | 1 | 12 |
| ETH-Jelmoli | 30.9 | 50.5 | 32.3 | 3 | 22 | 194 | 1,551 | 38.9 | 83.6 | 37.9 | 27.6 | 44.2 | 64.7 | 30.0 | 64.4 | 76.5 | 0.4 | 7 | 41 |
| ETH-Linthescher | 9.0 | 16.2 | 16.4 | 1 | 172 | 197 | 7,925 | 11.3 | 83.6 | 30.9 | 8.7 | 34.6 | 61.8 | 8.9 | 66.0 | 75.7 | 0.2 | 7 | 39 |
| KITTI-16 | 29.2 | 41.8 | 26.8 | 0 | 5 | 91 | 1,098 | 35.4 | 86.9 | 27.1 | 26.4 | 30.4 | 55.5 | 27.8 | 68.2 | 76.2 | 0.4 | 15 | 36 |
| KITTI-19 | 18.9 | 32.6 | 24.0 | 1 | 28 | 683 | 3,605 | 32.5 | 71.8 | 25.9 | 23.0 | 29.1 | 59.8 | 25.2 | 55.7 | 71.8 | 0.6 | 46 | 154 |
| PETS09-S2L2 | 28.9 | 31.0 | 22.2 | 0 | 14 | 662 | 6,086 | 36.9 | 84.3 | 19.1 | 26.1 | 20.7 | 59.4 | 27.7 | 63.3 | 73.5 | 1.5 | 104 | 218 |
| TUD-Crossing | 49.3 | 61.7 | 41.0 | 3 | 3 | 82 | 470 | 57.4 | 88.5 | 44.2 | 38.1 | 48.3 | 66.8 | 42.3 | 65.2 | 76.9 | 0.4 | 7 | 15 |
| Venice-1 | 14.8 | 33.0 | 25.3 | 1 | 8 | 621 | 3,259 | 28.6 | 67.7 | 32.7 | 19.7 | 34.4 | 72.7 | 22.4 | 53.1 | 76.5 | 1.4 | 9 | 54 |
Raw data:
